© 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. 1-RES-JB
    11. 20261
    Prev
    Next
    INDEX
    Explanations

    mentions of ballistic missiles

    oai_token-act-pair · gpt-3.5-turbo

    references to ballistic missiles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ween
    -0.85
    Place
    -0.80
    ths
    -0.78
    erva
    -0.75
    NAS
    -0.75
    gres
    -0.74
    Cert
    -0.73
    Pont
    -0.72
    lder
    -0.72
    bern
    -0.72
    POSITIVE LOGITS
     ballistic
    1.45
     missile
    1.28
     missiles
    1.25
     traject
    1.04
     projectiles
    1.00
     carbohyd
    0.87
     warheads
    0.87
     trajectory
    0.86
     gelatin
    0.86
     challeng
    0.85
    Activations Density 0.005%

    No Known Activations