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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 21760
    Prev
    Next
    INDEX
    Explanations

    mentions of specific tasks, roles, and locations related to law enforcement and government actions

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizational roles and structured entities involved in governance and service provision

    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
    Ô
    -1.15
    ORN
    -0.73
    peed
    -0.73
    stasy
    -0.72
    NetMessage
    -0.67
    Hash
    -0.67
     Speedway
    -0.67
    bows
    -0.65
     Wicked
    -0.64
     Bigfoot
    -0.64
    POSITIVE LOGITS
     office
    1.06
     secretary
    1.03
     officer
    1.01
     department
    1.00
     council
    0.94
     committee
    0.94
     councill
    0.90
     investigator
    0.89
     clerk
    0.88
     minister
    0.88
    Activations Density 0.310%

    No Known Activations