© 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. 8361
    Prev
    Next
    INDEX
    Explanations

    instances of agreements or deals between parties

    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
    +0.22
    0.7%
    253
    +0.14
    0.5%
    224
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.22
    0.06
    224
    +0.14
    0.06
    288
    +0.13
    0.07
    Negative Logits
    ãĥ©ãĥ³
    -1.03
    asus
    -1.02
    vae
    -1.00
     tremend
    -0.96
    si
    -0.94
     Stain
    -0.90
    stocks
    -0.89
    evil
    -0.87
    ixel
    -0.86
    cemic
    -0.86
    POSITIVE LOGITS
    breaker
    1.42
     breaker
    1.30
    ually
    1.26
    breakers
    1.25
     negotiated
    1.20
     agreements
    1.19
     agreement
    1.17
    reements
    1.15
     negotiator
    1.13
     treaties
    1.12
    Activations Density 0.896%

    No Known Activations