© 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. 10-RES-JB
    11. 12880
    Prev
    Next
    INDEX
    Explanations

    numerical values, likely related to metrics or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with content engagement metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pex
    -0.65
    dq
    -0.63
    -.
    -0.63
     MacArthur
    -0.63
    gomery
    -0.61
    rolet
    -0.61
    iday
    -0.61
     suppose
    -0.61
    orno
    -0.60
     Fey
    -0.59
    POSITIVE LOGITS
     votes
    0.83
     replies
    0.74
     views
    0.74
     posts
    0.71
     comments
    0.69
     Likes
    0.68
     Reviews
    0.64
     mins
    0.64
    446
    0.62
     Words
    0.62
    Activations Density 0.086%

    No Known Activations