© 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. 6-RES-JB
    11. 11572
    Prev
    Next
    INDEX
    Explanations

    ratings or rankings

    oai_token-act-pair · gpt-3.5-turbo

    numerical ratings and rankings of various subjects

    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
    ibus
    -0.71
     impunity
    -0.68
    ipation
    -0.68
    ellar
    -0.67
     contact
    -0.63
    pat
    -0.60
    ĨĴ
    -0.60
    acas
    -0.60
    soever
    -0.59
    GREEN
    -0.58
    POSITIVE LOGITS
     percentile
    0.80
     Ratings
    0.80
    formance
    0.77
     Highest
    0.74
    geist
    0.74
     Enlight
    0.73
    eous
    0.71
    ocre
    0.71
    iculty
    0.69
     subjective
    0.69
    Activations Density 0.262%

    No Known Activations