© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 9458
    Prev
    Next
    INDEX
    Explanations

    keywords related to political and legislative contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and regulatory processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kish
    -0.77
    raz
    -0.76
    hm
    -0.74
    mere
    -0.73
    rail
    -0.73
    lon
    -0.73
    utch
    -0.73
    osh
    -0.73
    isc
    -0.72
    cean
    -0.70
    POSITIVE LOGITS
    URE
    1.35
    BOOK
    1.33
    LY
    1.30
    ION
    1.30
    INESS
    1.29
    ALLY
    1.27
    ING
    1.26
    NESS
    1.25
    ABLE
    1.25
    ARY
    1.25
    Activations Density 0.103%

    No Known Activations