© 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. 14133
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing or repeated actions

    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
    78
    +0.12
    0.5%
    113
    +0.12
    0.5%
    17
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    728
    +0.12
    0.06
    78
    +0.12
    0.06
    113
    +0.12
    0.05
    Negative Logits
    lights
    -0.82
    mares
    -0.81
    pu
    -0.81
    dt
    -0.78
    hog
    -0.78
    iewicz
    -0.78
    Tier
    -0.77
    flags
    -0.77
    sg
    -0.77
     Awakens
    -0.76
    POSITIVE LOGITS
    ggy
    0.90
    omething
    0.88
    pez
    0.87
     nothing
    0.84
     brisk
    0.84
    ored
    0.83
    berman
    0.81
     something
    0.81
    zed
    0.79
    omsday
    0.79
    Activations Density 0.632%

    No Known Activations