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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18718
    Prev
    Next
    INDEX
    Explanations

    sentences related to releases or announcements

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks that end sentences or express excitement

    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
     discouraged
    -0.75
     allowance
    -0.73
     outwe
    -0.72
     attrition
    -0.69
     livelihood
    -0.67
     dissu
    -0.65
     elbows
    -0.65
     contingency
    -0.65
     perspect
    -0.65
     grop
    -0.64
    POSITIVE LOGITS
     Featuring
    1.34
     Located
    1.16
     Released
    1.08
     Originally
    1.06
    eaturing
    1.06
     Created
    1.03
     Includes
    1.00
     Designed
    0.98
     This
    0.95
     Contains
    0.95
    Activations Density 0.441%

    No Known Activations