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. 12151
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    actions related to processes and outcomes

    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
    otin
    -0.82
    rists
    -0.63
    anche
    -0.62
    asio
    -0.61
     celebr
    -0.60
    ndra
    -0.60
     Freak
    -0.59
    shoot
    -0.58
    iggins
    -0.58
     Dian
    -0.57
    POSITIVE LOGITS
     versus
    1.04
     depends
    1.04
    ?,
    1.01
     compared
    0.97
     varies
    0.95
     differs
    0.87
    ?:
    0.86
     differed
    0.82
    ?
    0.82
    Tokens
    0.81
    Activations Density 0.683%

    No Known Activations