© 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. 4-RES-JB
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    mentions of violent or cruel acts

    oai_token-act-pair · gpt-3.5-turbo

    references to violence or severe harm

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

    No Comments

    Negative Logits
    cript
    -0.78
    annis
    -0.75
    ploma
    -0.73
    kj
    -0.73
    verage
    -0.72
    leaf
    -0.72
    OPLE
    -0.71
    FU
    -0.71
     Libraries
    -0.70
    BU
    -0.68
    POSITIVE LOGITS
     earthqu
    0.91
    ized
    0.90
     assault
    0.85
     beasts
    0.85
     killers
    0.82
     assaults
    0.80
     punishments
    0.80
     dictator
    0.79
     murdering
    0.78
     murders
    0.78
    Activations Density 0.017%

    No Known Activations