© 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 EvalsExportsinterp-engineNEWAPI 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. 7546
    Prev
    Next
    INDEX
    Explanations

    information related to specific events or situations happening

    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
    160
    +0.15
    0.5%
    642
    +0.14
    0.4%
    538
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.15
    0.04
    309
    +0.14
    0.04
    303
    +0.14
    0.04
    Negative Logits
    gee
    -1.25
    bern
    -1.18
    pless
    -1.13
    emale
    -1.11
    velop
    -1.10
    irst
    -1.06
    obook
    -1.05
    OAD
    -1.03
    iary
    -1.02
    geon
    -0.99
    POSITIVE LOGITS
     happened
    1.59
     transpired
    1.41
     happens
    1.39
     happen
    1.37
     happening
    1.32
     happ
    1.26
     Happ
    1.19
     matters
    1.12
     occurred
    1.08
     toget
    1.08
    Activations Density 0.730%

    No Known Activations