© 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. 375
    Prev
    Next
    INDEX
    Explanations

    information related to pricing, dates, and terms in a text

    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
    31
    +0.10
    0.5%
    277
    +0.07
    0.4%
    486
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    703
    +0.10
    0.03
    172
    +0.07
    0.03
    739
    +0.07
    0.02
    Negative Logits
    =-=-=-=-=-=-=-=-
    -0.68
    Console
    -0.67
    ulner
    -0.66
    soc
    -0.64
    xit
    -0.62
    esides
    -0.61
    Switch
    -0.60
    oppable
    -0.58
     nevertheless
    -0.58
    XT
    -0.58
    POSITIVE LOGITS
     Schumer
    0.61
     Roosevelt
    0.60
     ordering
    0.56
     generous
    0.55
     comma
    0.55
    agraph
    0.52
     Dickinson
    0.52
     mandatory
    0.51
     Rue
    0.51
     Shaw
    0.50
    Activations Density 0.240%

    No Known Activations