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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4145
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly those with double-barrel names or initials

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.80
    isSpecialOrderable
    -0.73
    minecraft
    -0.72
    ftime
    -0.64
    schild
    -0.63
    cular
    -0.61
    arez
    -0.60
    inki
    -0.60
    aida
    -0.57
    kefeller
    -0.57
    POSITIVE LOGITS
    vez
    0.75
    acter
    0.73
    abbage
    0.72
    neau
    0.71
    Administ
    0.67
    Esc
    0.66
    onential
    0.66
    auga
    0.64
    ottesville
    0.64
    ij士
    0.64
    Activations Density 0.438%

    No Known Activations