© 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. 10-RES-JB
    11. 12789
    Prev
    Next
    INDEX
    Explanations

    -incidents that require police involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to police activity and responses to incidents

    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
    gemony
    -0.63
     Publisher
    -0.62
     Ranking
    -0.62
     Journals
    -0.59
    TPP
    -0.59
    Ranked
    -0.59
    icipated
    -0.59
    peat
    -0.57
     Decay
    -0.57
    ãĥĻ
    -0.56
    POSITIVE LOGITS
     shortly
    1.00
     paramedics
    0.96
     alerted
    0.84
     investigating
    0.84
     urgently
    0.76
     immediately
    0.76
     patrolling
    0.75
     briefly
    0.75
     responding
    0.75
    EMS
    0.74
    Activations Density 0.119%

    No Known Activations