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. 23804
    Prev
    Next
    INDEX
    Explanations

    the name "Bercow"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific political figure, likely focusing on their statements or actions

    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
     ties
    -0.62
     opposite
    -0.62
     tie
    -0.60
     gloom
    -0.59
     melt
    -0.58
     unaff
    -0.58
     latch
    -0.58
     Holt
    -0.57
     TAM
    -0.57
     Frey
    -0.57
    POSITIVE LOGITS
    erc
    4.75
    ERC
    2.10
    ercise
    1.84
    ert
    1.55
    orc
    1.23
    ering
    1.19
    erg
    1.18
     exerc
    1.14
    erv
    1.14
    erto
    1.12
    Activations Density 0.014%

    No Known Activations