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. 3-RES-JB
    6. 22127
    Prev
    Next
    INDEX
    Explanations

    terms related to various committees or commissions

    oai_token-act-pair · gpt-3.5-turbo

    references to committees or commissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lings
    -0.76
     Balk
    -0.70
     Cinderella
    -0.68
    ted
    -0.64
     Borderlands
    -0.64
     Kubrick
    -0.63
    uca
    -0.63
     Lank
    -0.61
     Blumenthal
    -0.60
     DAM
    -0.60
    POSITIVE LOGITS
    ittee
    1.24
    onsense
    1.10
    ittees
    1.05
    issions
    1.03
    odore
    1.03
    puter
    1.00
    itted
    0.99
    otion
    0.98
    ittal
    0.97
    ander
    0.97
    Activations Density 0.007%

    No Known Activations