© 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. 11-RES-JB
    11. 3832
    Prev
    Next
    INDEX
    Explanations

    emergency contact information such as hotlines and crime reporting numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references to crime statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bends
    -0.77
     wob
    -0.64
    gemony
    -0.63
     patents
    -0.62
     Ange
    -0.62
    hai
    -0.61
     symmetry
    -0.60
     licenses
    -0.60
    orate
    -0.59
     delegate
    -0.59
    POSITIVE LOGITS
    oppers
    1.07
     Crime
    0.96
     Crim
    0.94
    TI
    0.91
    TYPE
    0.90
    hovah
    0.85
    Crime
    0.84
    FBI
    0.83
    crime
    0.81
    tips
    0.79
    Activations Density 0.056%

    No Known Activations