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. 16188
    Prev
    Next
    INDEX
    Explanations

    phrases related to data analysis and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    content related to governmental performance and public health metrics

    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
    Sov
    -0.74
     externalToEVAOnly
    -0.72
    kos
    -0.65
    iao
    -0.64
    btn
    -0.63
    >[
    -0.62
    Tro
    -0.62
    cel
    -0.62
     endif
    -0.61
    ¨
    -0.61
    POSITIVE LOGITS
     respective
    0.85
     different
    0.83
     various
    0.81
     versus
    0.78
    levant
    0.75
     differed
    0.73
     Different
    0.73
     hypothetical
    0.72
     relevant
    0.72
     differing
    0.71
    Activations Density 0.662%

    No Known Activations