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. 19868
    Prev
    Next
    INDEX
    Explanations

    names containing the syllable "man"

    oai_token-act-pair · gpt-3.5-turbo

    the character "man" 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
    uesday
    -0.78
    avorite
    -0.66
    ÃįÃį
    -0.66
    urus
    -0.66
    CAST
    -0.66
    anked
    -0.63
    PsyNetMessage
    -0.63
    anyon
    -0.62
    ¥ŀ
    -0.62
    ORK
    -0.62
    POSITIVE LOGITS
    ifest
    1.38
    ufact
    1.17
    ning
    1.14
    uscript
    1.08
    iac
    1.05
    ned
    1.01
    hood
    0.96
    士
    0.94
    agements
    0.91
    iasis
    0.91
    Activations Density 0.038%

    No Known Activations