© 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. 6876
    Prev
    Next
    INDEX
    Explanations

    statements related to actions that should be taken or have been taken

    oai_token-act-pair · gpt-3.5-turbo

    punctuated phrases that include multiple instances of commas

    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
    ulz
    -0.72
    vre
    -0.71
    erest
    -0.66
    ospace
    -0.64
    iciency
    -0.63
    ierre
    -0.63
    thia
    -0.62
    ge
    -0.60
    hov
    -0.60
    ellar
    -0.60
    POSITIVE LOGITS
     albeit
    1.06
     namely
    0.83
     regardless
    0.70
    but
    0.70
     but
    0.70
     irrespective
    0.70
    albeit
    0.70
     viz
    0.69
     although
    0.68
     except
    0.67
    Activations Density 0.327%

    No Known Activations