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. 0-RES-JB
    6. 10977
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly the surname "Rodham."

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and terms associated with political figures and conditions

    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
    enger
    -0.96
    olar
    -0.81
    mat
    -0.80
    mong
    -0.80
    plex
    -0.79
    cell
    -0.77
    ilar
    -0.77
     transmission
    -0.77
    gran
    -0.75
    pan
    -0.73
    POSITIVE LOGITS
    ãģ«
    2.88
    ãĤĴ
    2.82
    ãģ®
    2.80
    ãģ¯
    2.80
    ãģĮ
    2.68
    ãģ§
    2.65
    ãģ¨
    2.50
    ãģ®å
    2.17
    ãĤĤ
    2.17
    ã쮿
    2.07
    Activations Density 0.038%

    No Known Activations