© 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. 6-RES-JB
    11. 19662
    Prev
    Next
    INDEX
    Explanations

    numeric values followed by their units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    quantitative metrics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Synopsis
    -0.71
    ormal
    -0.63
    ady
    -0.62
    gat
    -0.60
    imen
    -0.60
     Pulitzer
    -0.59
    bred
    -0.58
    values
    -0.58
    harm
    -0.57
    Wiki
    -0.56
    POSITIVE LOGITS
     increments
    1.04
     apiece
    0.97
    /$
    0.81
    alion
    0.80
    +.
    0.78
     thereafter
    0.73
    TPS
    0.73
     hers
    0.71
    osuke
    0.70
     rul
    0.70
    Activations Density 0.259%

    No Known Activations