© 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. 7-RES-JB
    11. 13346
    Prev
    Next
    INDEX
    Explanations

    mentions of weapons

    oai_token-act-pair · gpt-3.5-turbo

    references to weapons

    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
    gres
    -0.84
    apest
    -0.81
     Strawberry
    -0.77
    lus
    -0.75
     coli
    -0.71
    noon
    -0.71
    dit
    -0.69
    alg
    -0.69
    âĸ¬
    -0.67
    Adams
    -0.66
    POSITIVE LOGITS
    powder
    0.96
     caches
    0.89
     weapons
    0.89
     arsenal
    0.88
    manship
    0.86
     shipments
    0.82
    usable
    0.81
     smugglers
    0.81
     systems
    0.81
     manufacturer
    0.80
    Activations Density 0.036%

    No Known Activations