© 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. 21524
    Prev
    Next
    INDEX
    Explanations

    locations and details related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    connections to legal charges or actions

    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
    itar
    -0.76
    soever
    -0.71
    uge
    -0.69
    ï¸ı
    -0.69
    cients
    -0.68
     theoret
    -0.67
     globally
    -0.66
    izens
    -0.64
     Cosponsors
    -0.64
    Very
    -0.64
    POSITIVE LOGITS
     his
    1.59
     her
    1.32
     hers
    1.31
     himself
    1.25
    his
    1.13
     herself
    1.12
     him
    1.07
     HIS
    0.88
    His
    0.86
     bruises
    0.81
    Activations Density 0.526%

    No Known Activations