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. 10-RES-JB
    6. 19778
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions with serious consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the cancellation or suspension of activities or contracts

    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
    aceae
    -0.83
    hene
    -0.81
    achine
    -0.79
    iverse
    -0.77
    govtrack
    -0.76
    ertodd
    -0.73
    emonic
    -0.73
    Sov
    -0.72
    ernels
    -0.72
    ensity
    -0.71
    POSITIVE LOGITS
     plans
    0.96
     its
    0.91
     registrations
    0.84
     shipments
    0.83
     publication
    0.81
     production
    0.80
     offending
    0.79
     altogether
    0.79
     funding
    0.78
     refunds
    0.77
    Activations Density 0.221%

    No Known Activations