© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10507
    Prev
    Next
    INDEX
    Explanations

    legal and contractual terms related to agreements and the involvement of multiple parties in various situations

    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
    288
    +0.19
    0.7%
    417
    +0.15
    0.5%
    718
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.07
    247
    +0.15
    0.05
    318
    +0.15
    0.05
    Negative Logits
    iflower
    -1.03
    osis
    -0.91
    opia
    -0.90
    awar
    -0.88
     Bav
    -0.88
    ukong
    -0.87
     Gat
    -0.87
    frey
    -0.86
     Continental
    -0.85
    entric
    -0.85
    POSITIVE LOGITS
     involved
    1.14
     thereto
    1.10
    NetMessage
    1.06
     parties
    1.06
     pled
    1.05
    hood
    1.03
    ele
    1.01
    peak
    1.00
    hip
    0.99
    Party
    0.97
    Activations Density 0.753%

    No Known Activations