© 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. 7630
    Prev
    Next
    INDEX
    Explanations

    words related to driving and the act of driving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words relating to liquids running or dripping

    oai_token-act-pair · gpt-3.5-turbo
    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
    orative
    -0.79
    nets
    -0.78
    fish
    -0.75
    town
    -0.75
    RON
    -0.74
    olith
    -0.73
    anical
    -0.71
    rane
    -0.67
    folk
    -0.67
    wash
    -0.66
    POSITIVE LOGITS
    zzle
    1.02
    quet
    0.98
    xual
    0.89
    ijn
    0.84
    aging
    0.81
    ially
    0.73
    quel
    0.72
    zz
    0.72
    ousing
    0.69
    zona
    0.66
    Activations Density 0.105%

    No Known Activations