© 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. 303
    Prev
    Next
    INDEX
    Explanations

    questions or requests for information

    oai_token-act-pair · gpt-3.5-turbo

    phrases and questions that inquire about specific information or details

    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
    rex
    -0.74
    vier
    -0.65
    yrinth
    -0.65
    cheon
    -0.65
    rox
    -0.61
    gypt
    -0.60
    seless
    -0.59
    alla
    -0.59
    otal
    -0.57
    rained
    -0.57
    POSITIVE LOGITS
    THING
    1.22
    place
    0.97
     semblance
    0.93
    body
    0.92
    WHERE
    0.89
    ones
    0.89
    thin
    0.85
    how
    0.84
    ONE
    0.83
     doubts
    0.81
    Activations Density 0.074%

    No Known Activations