© 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. 8-RES-JB
    11. 12853
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes or sharing experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss the act of talking about various topics

    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
    kai
    -0.70
    omers
    -0.70
    kie
    -0.70
    irl
    -0.69
    HT
    -0.69
    OGR
    -0.68
    ©¶æ¥µ
    -0.68
    SPONSORED
    -0.67
     CLSID
    -0.66
    ï¸ı
    -0.66
    POSITIVE LOGITS
     how
    1.03
     reforming
    1.00
     topics
    0.85
     improving
    0.83
     quitting
    0.82
     preserving
    0.80
     specifics
    0.80
     overcoming
    0.79
     whether
    0.79
     wanting
    0.78
    Activations Density 0.103%

    No Known Activations