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. 0-RES-JB
    6. 17251
    Prev
    Next
    INDEX
    Explanations

    Java code comments that start with an asterisk

    oai_token-act-pair · gpt-3.5-turbo

    references to code or commands in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ews
    -0.78
    ',"
    -0.63
    ön
    -0.61
    ité
    -0.59
    ilant
    -0.57
    eworld
    -0.55
    OHN
    -0.54
     plunge
    -0.53
     dubbed
    -0.51
     thriller
    -0.50
    POSITIVE LOGITS
     *
    3.52
     **
    2.61
    *
    2.18
     *)
    2.00
     ***
    1.95
     */
    1.87
    .*
    1.86
     (*
    1.83
    )*
    1.82
     *.
    1.79
    Activations Density 0.006%

    No Known Activations