© 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. 8-RES-JB
    11. 6916
    Prev
    Next
    INDEX
    Explanations

    words related to the Wild West

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Wild" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vit
    -0.75
     mathemat
    -0.73
    akeru
    -0.73
     tremend
    -0.70
    awaru
    -0.69
    auga
    -0.68
    ately
    -0.67
    acist
    -0.67
    uyomi
    -0.65
     incap
    -0.65
    POSITIVE LOGITS
    erness
    1.36
    lings
    1.11
    rose
    1.05
    flower
    1.04
    fires
    1.01
    fire
    0.99
    enstein
    0.96
    cat
    0.94
    Tang
    0.94
    life
    0.92
    Activations Density 0.012%

    No Known Activations