Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1680
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions, inclusions, or specifications

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exceptions or inclusivity

    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
    ãĥ¼ãĥĨ
    -0.62
     Klu
    -0.56
    urion
    -0.55
    pload
    -0.53
    ription
    -0.52
     Tray
    -0.52
    ãĥ¼ãĥĨãĤ£
    -0.51
     tyr
    -0.51
     Peach
    -0.50
     Citiz
    -0.50
    POSITIVE LOGITS
    .
    0.95
    !
    0.88
    ;
    0.85
    .[
    0.85
    ãĢĤ
    0.84
     :)
    0.83
     ;)
    0.83
    .,
    0.82
    —
    0.79
     ðŁĺ
    0.79
    Activations Density 0.344%

    No Known Activations