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. 1543
    Prev
    Next
    INDEX
    Explanations

    names with the string "ough"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ough" in various contexts

    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
    jl
    -0.68
    uality
    -0.65
    HOU
    -0.63
     Luthor
    -0.61
    DNA
    -0.58
     Petra
    -0.58
    jri
    -0.58
     Takeru
    -0.58
    WHERE
    -0.57
    vier
    -0.57
    POSITIVE LOGITS
    tyard
    0.88
    sburgh
    0.86
    sburg
    0.85
    é¾įåĸļ士
    0.83
    hesda
    0.80
    nut
    0.77
    orst
    0.75
    ricanes
    0.74
    lins
    0.74
    ness
    0.74
    Activations Density 0.014%

    No Known Activations