© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 1525
    Prev
    Next
    INDEX
    Explanations

    financial information and details on organizations

    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
    416
    +0.03
    0.5%
    685
    +0.03
    0.4%
    695
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.03
    0.02
    398
    +0.03
    0.01
    29
    +0.03
    0.02
    Negative Logits
    Ĥİ
    -0.19
    task
    -0.19
    register
    -0.19
    security
    -0.19
    due
    -0.18
    storage
    -0.18
    exit
    -0.18
    form
    -0.18
    speech
    -0.18
     instant
    -0.18
    POSITIVE LOGITS
    athered
    0.22
    inav
    0.20
     Ames
    0.20
     HG
    0.19
    ONSORED
    0.19
     Beir
    0.18
     Gaw
    0.18
     Emblem
    0.18
    OUP
    0.18
     Ãĸ
    0.18
    Activations Density 0.052%

    No Known Activations