© 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. 6-RES-JB
    11. 9270
    Prev
    Next
    INDEX
    Explanations

    specific character sequences denoting a variety of entities, locations, and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and parentheses, indicating citation or reference structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     millenn
    -0.79
     stimulus
    -0.74
     volunte
    -0.71
    ellen
    -0.71
     footing
    -0.67
     undue
    -0.67
    elling
    -0.65
     conclud
    -0.64
     moms
    -0.64
     offenders
    -0.63
    POSITIVE LOGITS
    soDeliveryDate
    0.92
    pron
    0.80
    edu
    0.79
     Viz
    0.79
     Galile
    0.78
    sic
    0.77
    Shield
    0.76
     Saga
    0.76
     Healer
    0.75
    ãĥĪ
    0.75
    Activations Density 0.589%

    No Known Activations