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. 10-RES-JB
    6. 235
    Prev
    Next
    INDEX
    Explanations

    words related to ethics, politics, and criticism

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and cultural critique

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.74
    imately
    -0.74
    cipled
    -0.71
    ificantly
    -0.70
    ually
    -0.67
     probable
    -0.67
     suspended
    -0.66
     secured
    -0.66
     authorised
    -0.66
     contracted
    -0.66
    POSITIVE LOGITS
    tones
    1.17
    ieties
    1.10
    usions
    1.07
    isms
    1.05
    otypes
    1.04
    ographies
    1.03
    unctions
    0.96
    aunts
    0.93
    notations
    0.93
    izons
    0.92
    Activations Density 0.321%

    No Known Activations