© 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. 3-RES-JB
    11. 10789
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement officers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "cop"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -1.01
    FORE
    -0.88
    schild
    -0.76
    Downloadha
    -0.76
    veyard
    -0.71
    */(
    -0.70
    xual
    -0.67
    hower
    -0.65
    WAY
    -0.65
    pport
    -0.64
    POSITIVE LOGITS
    yrights
    1.27
    rodu
    1.01
    yright
    0.99
    ious
    0.92
    enhagen
    0.91
    yp
    0.91
     cop
    0.89
    icker
    0.85
    eland
    0.79
    rol
    0.79
    Activations Density 0.003%

    No Known Activations