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. 3791
    Prev
    Next
    INDEX
    Explanations

    mentions of the CBS network

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the CBS network

    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
    ainer
    -0.82
    arist
    -0.75
    aced
    -0.73
    antly
    -0.71
    istry
    -0.70
    arity
    -0.70
    lain
    -0.69
    htaking
    -0.69
    rha
    -0.66
    isites
    -0.66
    POSITIVE LOGITS
     Evening
    0.95
    DAQ
    0.95
     News
    0.94
     Interactive
    0.93
    Sports
    0.92
    IRO
    0.91
     Broadcasting
    0.84
    NEWS
    0.84
    News
    0.82
     Corp
    0.80
    Activations Density 0.013%

    No Known Activations