© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 12208
    Prev
    Next
    INDEX
    Explanations

    words related to legal and government matters, such as court cases, laws, government actions, and law enforcement activities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    224
    +0.18
    0.6%
    724
    +0.17
    0.5%
    718
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.18
    0.08
    423
    +0.17
    0.08
    706
    +0.16
    0.07
    Negative Logits
    atche
    -1.08
    Lex
    -1.06
    aspx
    -1.05
    toc
    -0.97
     Obj
    -0.96
    usercontent
    -0.96
    plet
    -0.96
     Patch
    -0.94
    Pages
    -0.94
     liner
    -0.93
    POSITIVE LOGITS
     fascinated
    1.42
    theless
    1.29
     puzzled
    1.24
     championed
    1.09
     intrigued
    1.08
     baffled
    1.08
     entertained
    1.08
     embraced
    1.06
     regarded
    1.05
     amazed
    1.04
    Activations Density 0.986%

    No Known Activations