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. 20997
    Prev
    Next
    INDEX
    Explanations

    specific years or acts of legislation

    oai_token-act-pair · gpt-3.5-turbo

    references to legislative acts and their corresponding years

    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
     sympath
    -0.67
     specialize
    -0.67
     Inquis
    -0.66
     knot
    -0.65
    ngth
    -0.65
    english
    -0.62
    axter
    -0.61
     foss
    -0.61
     slay
    -0.60
     task
    -0.60
    POSITIVE LOGITS
     1974
    1.25
     1958
    1.20
     1973
    1.18
     1978
    1.18
     1988
    1.14
     1994
    1.13
     1971
    1.12
     2014
    1.12
     1965
    1.12
     1975
    1.12
    Activations Density 0.067%

    No Known Activations