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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 10-RES-JB
    6. 10963
    Prev
    Next
    INDEX
    Explanations

    phrases describing or identifying people and situations

    oai_token-act-pair · gpt-3.5-turbo

    references to descriptions and evaluations of people or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ework
    -0.60
    vre
    -0.50
    ggles
    -0.46
    vl
    -0.46
     dstg
    -0.46
    redo
    -0.46
     somet
    -0.45
    oret
    -0.45
     tide
    -0.44
     Clicker
    -0.43
    POSITIVE LOGITS
     as
    1.62
    as
    1.17
    As
    0.90
     As
    0.86
     AS
    0.78
    asher
    0.78
     alongside
    0.75
     favorably
    0.70
    AS
    0.62
    asin
    0.61
    Activations Density 1.008%

    No Known Activations