Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20355
    Prev
    Next
    INDEX
    Explanations

    words related to ballistic missiles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ballistic missile technology and tests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.81
    liness
    -0.79
    vier
    -0.77
    ween
    -0.76
    Place
    -0.75
     Wond
    -0.73
    ugen
    -0.72
    fol
    -0.72
    ths
    -0.72
    isans
    -0.72
    POSITIVE LOGITS
     missile
    1.19
     missiles
    1.18
     ballistic
    1.15
     traject
    1.02
     projectiles
    0.91
     weapons
    0.83
    imentary
    0.79
     weaponry
    0.78
     batteries
    0.77
     warheads
    0.77
    Activations Density 0.011%

    No Known Activations