© 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. 6834
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters with special symbols in between them, potentially related to code or technical information

    oai_token-act-pair · gpt-3.5-turbo

    numerical measurements and physical dimensions

    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
     Kepler
    -0.66
    eele
    -0.65
    lé
    -0.62
    ufact
    -0.59
     prol
    -0.58
     Sylvia
    -0.58
     deceive
    -0.58
     maternal
    -0.57
     achievement
    -0.56
     gull
    -0.56
    POSITIVE LOGITS
    thur
    0.85
    adelphia
    0.77
    emp
    0.76
    Chan
    0.74
    ornia
    0.73
    irez
    0.72
    inches
    0.72
    fig
    0.69
    months
    0.68
    USD
    0.68
    Activations Density 0.184%

    No Known Activations