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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 1644
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-3.5-turbo

    key actions or events that signify significant outcomes or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨ
    -0.63
     incent
    -0.62
     princ
    -0.62
     deem
    -0.62
     councill
    -0.62
    ò
    -0.60
     teasp
    -0.60
     citiz
    -0.59
     pione
    -0.58
     env
    -0.58
    POSITIVE LOGITS
    .
    1.11
    .;
    1.05
    .:
    1.03
    .,
    1.02
    .?
    0.98
    .-
    0.97
    .–
    0.92
    .(
    0.87
    .--
    0.83
    ./
    0.81
    Activations Density 0.372%

    No Known Activations