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. 7-RES-JB
    6. 16189
    Prev
    Next
    INDEX
    Explanations

    statistics or measurements related to performance

    oai_token-act-pair · gpt-3.5-turbo

    references to past seasons or events in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ordes
    -0.69
    âĶģ
    -0.69
    ongs
    -0.67
    roots
    -0.67
    ansk
    -0.66
    aunders
    -0.65
    cil
    -0.64
    oola
    -0.63
    /#
    -0.61
    ollow
    -0.61
    POSITIVE LOGITS
     week
    1.10
     month
    0.99
     year
    0.97
     semester
    0.92
     season
    0.89
     ditch
    0.85
     decade
    0.82
     Month
    0.82
     night
    0.80
     century
    0.77
    Activations Density 0.065%

    No Known Activations