© 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 EvalsExportsinterp-engineNEWAPI 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. 2839
    Prev
    Next
    INDEX
    Explanations

    websites and web addresses

    oai_token-act-pair · gpt-3.5-turbo

    web addresses or domains related to various topics

    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
    :]
    -0.63
     indign
    -0.58
    ensibly
    -0.58
     ridiculed
    -0.56
    Īè
    -0.56
     disparate
    -0.55
     fuss
    -0.55
     mass
    -0.54
     mirac
    -0.54
     clashed
    -0.54
    POSITIVE LOGITS
    /.
    1.49
    /,
    1.30
    /#
    1.08
     Alternatively
    1.08
    /?
    1.08
     .
    1.00
     Follow
    0.98
    <|endoftext|>
    0.91
    /+
    0.90
    /)
    0.90
    Activations Density 0.099%

    No Known Activations