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. 0-RES-JB
    6. 14030
    Prev
    Next
    INDEX
    Explanations

    mentions of people with the title "Dean"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dean"

    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
     multip
    -0.80
    fal
    -0.74
    hered
    -0.72
    TOR
    -0.69
    gew
    -0.68
    λ
    -0.67
     mosa
    -0.66
     âľĶ
    -0.65
     Bers
    -0.65
    tera
    -0.64
    POSITIVE LOGITS
     Dean
    3.68
    Dean
    3.05
     dean
    1.66
     Earl
    1.34
     Crowley
    1.22
     Rollins
    1.20
     Winchester
    1.19
     Metatron
    1.18
     Winc
    1.09
     Bray
    1.06
    Activations Density 0.017%

    No Known Activations