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

    Neuronpedia

    Jacobian LensNEW
    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. 20598
    Prev
    Next
    INDEX
    Explanations

    details of violent or criminal incidents

    oai_token-act-pair · gpt-3.5-turbo

    incidents related to self-defense or violent confrontations

    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
     optim
    -0.74
    optim
    -0.73
     UNESCO
    -0.69
     dividends
    -0.69
     Remastered
    -0.69
    ãĤ´ãĥ³
    -0.65
    lore
    -0.61
    gravity
    -0.61
    Tokens
    -0.61
     ç¥ŀ
    -0.59
    POSITIVE LOGITS
     altercation
    1.12
     gunfire
    1.09
     robbery
    1.09
     burglary
    1.09
     police
    1.04
     gunshots
    1.01
     burgl
    1.01
     homicide
    0.98
     robbers
    0.96
     arrest
    0.96
    Activations Density 1.396%

    No Known Activations