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. 6-RES-JB
    6. 16675
    Prev
    Next
    INDEX
    Explanations

    fast-paced, action-related terms

    oai_token-act-pair · gpt-3.5-turbo

    descriptors that indicate the characteristics or status of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orthy
    -0.91
    chwitz
    -0.85
    redits
    -0.84
    uther
    -0.79
    Specific
    -0.77
    atches
    -0.74
    drug
    -0.71
    stri
    -0.71
    cius
    -0.69
    rows
    -0.69
    POSITIVE LOGITS
     nature
    1.08
     version
    0.91
     saga
    0.84
     portion
    0.82
     duo
    0.77
     moniker
    0.77
     aspect
    0.77
     underside
    0.77
     phenomenon
    0.76
     onslaught
    0.76
    Activations Density 0.255%

    No Known Activations