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

    Neuronpedia

    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. 7-RES-JB
    11. 21820
    Prev
    Next
    INDEX
    Explanations

    words related to police, law enforcement, and legal terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to law enforcement and police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istic
    -0.70
    ħĭ
    -0.70
    lessly
    -0.70
    brush
    -0.67
    ista
    -0.66
    istas
    -0.66
    hide
    -0.65
    ists
    -0.62
    isting
    -0.62
     CONTROL
    -0.61
    POSITIVE LOGITS
    iple
    1.06
    geoning
    0.90
    emen
    0.85
    eworks
    0.83
    soDeliveryDate
    0.82
    escent
    0.78
    eless
    0.77
    ecast
    0.73
    onymous
    0.72
    uously
    0.72
    Activations Density 0.075%

    No Known Activations