© 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. 2-RES-JB
    11. 12930
    Prev
    Next
    INDEX
    Explanations

    numeric codes and abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to general-purpose computing and GPIO-related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jolly
    -0.76
    lined
    -0.76
    brate
    -0.65
     WARN
    -0.63
    brates
    -0.62
     Rite
    -0.61
     PATH
    -0.60
    folk
    -0.60
    line
    -0.59
    mare
    -0.59
    POSITIVE LOGITS
    GP
    1.22
    gp
    0.97
    HS
    0.86
    unal
    0.82
    odcast
    0.82
    ND
    0.82
    APH
    0.80
    arser
    0.79
    rint
    0.77
    OTO
    0.77
    Activations Density 0.009%

    No Known Activations