© 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. 2754
    Prev
    Next
    INDEX
    Explanations

    words related to "Strat" as a prefix or part of a longer word

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Stratford" and its variations

    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
     Clicker
    -0.89
    er
    -0.71
    Accessory
    -0.67
    DER
    -0.64
    urrent
    -0.63
    VICE
    -0.62
    activation
    -0.59
     Slate
    -0.59
    士
    -0.59
    Prosecutors
    -0.59
    POSITIVE LOGITS
    itud
    1.06
    astically
    0.97
    itudes
    0.96
    itude
    0.96
    astical
    0.94
    ilda
    0.92
    imore
    0.90
    osphere
    0.87
    oday
    0.86
    osp
    0.86
    Activations Density 0.091%

    No Known Activations