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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9849
    Prev
    Next
    INDEX
    Explanations

    items related to specific entities, events, or locations - possibly names of companies or institutions

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements that end in punctuation marks, indicating conclusions or final thoughts

    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
    axy
    -0.74
     attrition
    -0.73
     stray
    -0.70
     deterrent
    -0.69
     deterrence
    -0.67
    iation
    -0.67
    urance
    -0.66
    agons
    -0.66
    iga
    -0.65
     inexper
    -0.65
    POSITIVE LOGITS
     Featuring
    1.12
     NOTE
    1.12
     Accessed
    1.10
     Includes
    1.06
     Retrieved
    1.03
     Congratulations
    1.02
     Published
    1.02
     Recorded
    0.97
    blogspot
    0.96
    ↵Âł
    0.96
    Activations Density 0.473%

    No Known Activations