© 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. 428
    Prev
    Next
    INDEX
    Explanations

    sentences containing attributions, quotes, or reported speech

    oai_token-act-pair · gpt-3.5-turbo

    the presence of quoted speech in the text

    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
     Salem
    -0.72
     Reincarn
    -0.68
    VERTISEMENT
    -0.67
     SH
    -0.66
     Pur
    -0.66
     CPC
    -0.64
     Presidential
    -0.64
    HCR
    -0.64
     Chennai
    -0.64
     Bronx
    -0.63
    POSITIVE LOGITS
    âĢ¦]
    1.16
    ...]
    1.12
    english
    0.96
    ftime
    0.94
    ety
    0.91
    %]
    0.80
    ideshow
    0.78
    entimes
    0.72
    gypt
    0.71
    REDACTED
    0.70
    Activations Density 0.015%

    No Known Activations