© 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. 3201
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of legal cases involving arrests or criminal activity

    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
     conventions
    -0.76
     flattering
    -0.76
    ensical
    -0.70
     prediction
    -0.68
     endorsements
    -0.67
    Ide
    -0.65
     reservations
    -0.62
    casters
    -0.61
     nominating
    -0.60
     assumptions
    -0.60
    POSITIVE LOGITS
     aka
    0.92
    pictured
    0.89
     pictured
    0.84
     convicted
    0.82
     jailed
    0.82
     unlawfully
    0.81
     Sr
    0.80
     alias
    0.78
     arrested
    0.77
     aged
    0.77
    Activations Density 0.317%

    No Known Activations