© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10302
    Prev
    Next
    INDEX
    Explanations

    quotations within texts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of quotes and related metadata in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    agos
    -0.83
    aucas
    -0.74
    oulos
    -0.70
    hop
    -0.70
     lips
    -0.68
    rams
    -0.67
     Rohing
    -0.66
    ult
    -0.66
    collar
    -0.66
     surrog
    -0.65
    POSITIVE LOGITS
     Originally
    1.03
     Quote
    0.88
    Quote
    0.78
     Posted
    0.77
     Edited
    0.73
     ·
    0.70
     Reply
    0.69
     Developer
    0.68
     Investigator
    0.68
     Hi
    0.67
    Activations Density 0.045%

    No Known Activations