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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7646
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals, particularly names including "uma" at various frequencies

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Zuma" and related mentions in the context of political discussions

    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
    sburgh
    -0.73
    ician
    -0.70
    cies
    -0.68
    ¯¯¯¯
    -0.67
    ications
    -0.66
    ingham
    -0.66
    draw
    -0.66
    lean
    -0.64
    landish
    -0.64
    igree
    -0.64
    POSITIVE LOGITS
    UGH
    0.82
    ULT
    0.80
    pty
    0.70
     tion
    0.68
    uay
    0.66
    ĺħ
    0.65
     Abedin
    0.65
    asar
    0.64
    uds
    0.63
    zyk
    0.62
    Activations Density 0.056%

    No Known Activations