© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4228
    Prev
    Next
    INDEX
    Explanations

    proper nouns and corresponding punctuation marks as they appear at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥µ
    -0.76
    acly
    -0.72
     ("
    -0.71
    ahime
    -0.68
    negie
    -0.66
    roximately
    -0.61
    —"
    -0.60
     "
    -0.58
    avored
    -0.58
    rely
    -0.58
    POSITIVE LOGITS
     '.
    2.18
    ,'
    2.13
     ',
    2.10
    .'
    2.09
    ?'
    2.08
    ','
    1.99
    ';
    1.96
     '[
    1.92
    ',
    1.91
    '.
    1.90
    Activations Density 0.216%

    No Known Activations