Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 3679
    Prev
    Next
    INDEX
    Explanations

    vague phrases related to an unspecified subject, such as "an undefined one" or "bad way"

    oai_token-act-pair · gpt-3.5-turbo

    words related to numbers and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tyr
    -0.63
     acknow
    -0.60
    "))
    -0.55
    aughed
    -0.53
     fitt
    -0.50
    oggles
    -0.50
    ggles
    -0.49
     impunity
    -0.47
     Defin
    -0.47
     fail
    -0.47
    POSITIVE LOGITS
    ,
    1.11
    *,
    1.04
    .,
    1.04
    ,.
    1.00
    !,
    0.99
    _.
    0.97
    .
    0.96
    *.
    0.94
    ,...
    0.88
     respectively
    0.87
    Activations Density 0.523%

    No Known Activations