© 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. 8-RES-JB
    11. 17037
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases and terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perm
    -0.69
    gered
    -0.61
    redo
    -0.59
    KER
    -0.57
    CHECK
    -0.57
     Disabled
    -0.57
    AIR
    -0.57
     impunity
    -0.57
    sted
    -0.55
    ERY
    -0.55
    POSITIVE LOGITS
     dots
    1.02
     disparate
    0.92
     into
    0.82
    into
    0.80
     favorably
    0.78
    MpServer
    0.77
     seamlessly
    0.73
     perspectives
    0.73
     geographically
    0.72
     onto
    0.68
    Activations Density 0.380%

    No Known Activations