Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21885
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Comm" or variations like "Commision" or "Commitment"

    oai_token-act-pair · gpt-3.5-turbo

    references to committees or group organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lings
    -0.74
     Kubrick
    -0.68
    chest
    -0.67
     Balk
    -0.66
    loo
    -0.66
    BuyableInstoreAndOnline
    -0.65
     Piercing
    -0.63
     Manz
    -0.63
     Corinth
    -0.63
     Cinderella
    -0.62
    POSITIVE LOGITS
    ittee
    1.21
    uters
    1.11
    ission
    1.11
    otion
    1.09
    itted
    1.09
    issions
    1.09
    onsense
    1.08
    ourse
    1.08
    ittees
    1.07
    ittal
    1.04
    Activations Density 0.013%

    No Known Activations