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. 5-RES-JB
    6. 11309
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures named "Muammar Gaddafi."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals named "Mu" or related characters

    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
     Eleven
    -0.72
     wip
    -0.71
    å§«
    -0.71
     BART
    -0.69
    */(
    -0.69
     Dispatch
    -0.66
     Ajax
    -0.64
     UID
    -0.63
     Otto
    -0.63
     Carney
    -0.62
    POSITIVE LOGITS
    lder
    1.19
    zik
    1.03
    ahah
    1.03
    hammad
    1.00
    selage
    0.96
    udge
    0.96
     Klux
    0.95
    jah
    0.95
    osh
    0.93
    gha
    0.93
    Activations Density 0.008%

    No Known Activations