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. 8-RES-JB
    6. 9702
    Prev
    Next
    INDEX
    Explanations

    mentions of the abbreviation "CS" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to "CS," indicating a focus on computer science-related topics or classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ously
    -0.78
     Mandela
    -0.68
    fitted
    -0.65
     Hearts
    -0.60
    erers
    -0.60
     persu
    -0.60
    iating
    -0.60
     wills
    -0.60
    edged
    -0.58
     indebted
    -0.57
    POSITIVE LOGITS
    IRO
    1.10
    GO
    0.97
    RF
    0.95
    DP
    0.93
    MX
    0.92
    hent
    0.88
    DF
    0.85
    ULAR
    0.84
    CEPT
    0.83
    DN
    0.83
    Activations Density 0.026%

    No Known Activations