© 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
    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. 13771
    Prev
    Next
    INDEX
    Explanations

    USB-related terms and details

    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
    569
    +0.17
    0.6%
    167
    +0.17
    0.6%
    288
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.05
    288
    +0.17
    0.06
    343
    +0.16
    0.04
    Negative Logits
    anamo
    -1.12
    xual
    -1.08
    nces
    -1.05
    xon
    -1.05
    kamp
    -1.05
    ebin
    -1.03
    lain
    -0.99
    oles
    -0.99
    terday
    -0.98
    ym
    -0.98
    POSITIVE LOGITS
    UE
    1.10
    TN
    1.02
    TABLE
    1.00
    FFER
    0.98
    DP
    0.96
    PLIC
    0.96
    PF
    0.92
     Ports
    0.92
    YA
    0.91
     thumb
    0.91
    Activations Density 0.491%

    No Known Activations