© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 7478
    Prev
    Next
    INDEX
    Explanations

    descriptions of products or services that offer alternatives or customization options

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms indicating a search for unique or alternative options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    poll
    -0.78
     Committees
    -0.72
    ogenesis
    -0.71
     Cosponsors
    -0.69
    Beck
    -0.69
     Plaint
    -0.68
    redits
    -0.65
     Said
    -0.63
    occup
    -0.62
    omin
    -0.61
    POSITIVE LOGITS
     refres
    1.14
     adventurous
    0.91
     smoother
    0.90
     finer
    0.90
     sanity
    0.89
     cheaper
    0.88
     DIY
    0.87
     deeper
    0.85
     tactile
    0.85
     cheap
    0.84
    Activations Density 0.236%

    No Known Activations