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. 2127
    Prev
    Next
    INDEX
    Explanations

    mentions of legal actions such as pardon, deportation, and freeing individuals from legal consequences

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with legal pardons and deportations

    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
    pants
    -0.78
    acent
    -0.69
    oken
    -0.67
     SEM
    -0.66
     Dunk
    -0.66
    mop
    -0.63
    ideshow
    -0.61
     bra
    -0.59
    ibaba
    -0.59
    opers
    -0.59
    POSITIVE LOGITS
     pard
    0.89
     pardon
    0.86
     revocation
    0.81
    vous
    0.77
     deported
    0.77
    chwitz
    0.76
    20439
    0.75
    give
    0.74
    itives
    0.73
    ilege
    0.73
    Activations Density 0.090%

    No Known Activations