© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 12590
    Prev
    Next
    INDEX
    Explanations

    dates or time periods indicated by "BC" in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the designation "BC" as a historical time marker

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -1.16
    ãĤ¯
    -0.79
    ãĥŀ
    -0.73
    geant
    -0.72
    ners
    -0.71
    éĹĺ
    -0.71
    ktop
    -0.70
    stice
    -0.69
    strument
    -0.69
    perature
    -0.69
    POSITIVE LOGITS
    rypt
    0.79
    RC
    0.77
    FW
    0.76
    AMP
    0.76
    Ħ¢
    0.74
    elsius
    0.74
    orne
    0.74
     Hydro
    0.73
    RA
    0.73
    ascade
    0.73
    Activations Density 0.005%

    No Known Activations