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

    Neuronpedia

    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. 5703
    Prev
    Next
    INDEX
    Explanations

    legal and argumentative language

    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
    679
    +0.24
    0.8%
    195
    +0.20
    0.7%
    447
    +0.16
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.24
    0.05
    70
    +0.20
    0.09
    679
    +0.16
    0.09
    Negative Logits
    mental
    -0.89
     ILCS
    -0.88
    =~=~
    -0.88
    fell
    -0.88
    ptoms
    -0.85
     Announce
    -0.85
    kn
    -0.84
    obos
    -0.81
    beam
    -0.81
    of
    -0.80
    POSITIVE LOGITS
     bitterly
    1.12
     vehemently
    1.12
    inet
    1.07
     passionately
    1.06
     forcefully
    1.02
     convinc
    1.01
    rier
    0.96
     stren
    0.96
     arguing
    0.92
     persu
    0.91
    Activations Density 1.178%

    No Known Activations