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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 18943
    Prev
    Next
    INDEX
    Explanations

    numerical codes or identifiers embedded in the text

    oai_token-act-pair · gpt-3.5-turbo

    numerical values, specifically model or component identifiers

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

    No Comments

    Negative Logits
     snowball
    -0.76
     Oath
    -0.66
    querque
    -0.65
    ggies
    -0.62
    ogene
    -0.60
     plateau
    -0.60
    iri
    -0.60
    unia
    -0.60
     Yelp
    -0.60
    ifully
    -0.60
    POSITIVE LOGITS
    DM
    0.86
    CAP
    0.86
    XX
    0.86
    CB
    0.82
    XXX
    0.81
    VB
    0.81
    01
    0.80
    DX
    0.80
    014
    0.80
    651
    0.79
    Activations Density 0.099%

    No Known Activations