© 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. 9-RES-JB
    11. 13174
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent incidents or attacks

    oai_token-act-pair · gpt-3.5-turbo

    references to violent incidents or assaults

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bilt
    -0.72
     definition
    -0.61
    LESS
    -0.61
    definition
    -0.60
     Balance
    -0.59
    nosis
    -0.58
    access
    -0.58
     substitutes
    -0.57
    Option
    -0.56
     essence
    -0.55
    POSITIVE LOGITS
    uggest
    1.13
    hops
    1.09
    poons
    1.06
    uits
    1.06
    hips
    1.04
    creen
    1.03
    hots
    1.02
    hooting
    1.01
    cape
    1.00
    hip
    0.98
    Activations Density 0.301%

    No Known Activations