© 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. 4-RES-JB
    11. 6041
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing assertiveness or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically apostrophes

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

    No Comments

    Negative Logits
     eclipse
    -0.75
    conservancy
    -0.64
    isphere
    -0.63
    rador
    -0.60
     sidel
    -0.60
     transpl
    -0.56
    clipse
    -0.56
     cycle
    -0.56
     lapse
    -0.55
    ynski
    -0.54
    POSITIVE LOGITS
    ',
    0.78
    nai
    0.77
    Brien
    0.76
    MIC
    0.75
    alon
    0.74
    nos
    0.74
    Mech
    0.71
    Cause
    0.70
    bor
    0.70
    -'
    0.70
    Activations Density 0.050%

    No Known Activations