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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3686
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
    245
    +0.16
    0.5%
    530
    +0.15
    0.4%
    432
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.06
    57
    +0.15
    0.04
    67
    +0.14
    0.05
    Negative Logits
     Debor
    -1.21
    etsk
    -1.00
     msec
    -0.97
    icity
    -0.95
     Genie
    -0.93
     ko
    -0.91
     harb
    -0.89
     embargo
    -0.88
    framework
    -0.88
     bell
    -0.86
    POSITIVE LOGITS
    imore
    1.09
    anche
    1.05
    FS
    1.04
    NetMessage
    1.02
    oby
    1.02
    SL
    1.00
    OTOS
    0.99
    BIP
    0.93
    isode
    0.93
    STE
    0.91
    Activations Density 0.465%

    No Known Activations