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. 3-RES-JB
    6. 18677
    Prev
    Next
    INDEX
    Explanations

    visual or descriptive comparisons

    oai_token-act-pair · gpt-3.5-turbo

    phrases and comparisons indicating resemblance or similarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cius
    -0.79
    Ö¼
    -0.71
    inguished
    -0.71
    inction
    -0.65
    anting
    -0.65
    planned
    -0.63
    shire
    -0.61
    clerosis
    -0.61
    usting
    -0.61
    Requ
    -0.60
    POSITIVE LOGITS
    soDeliveryDate
    0.88
     favorably
    0.87
    TextColor
    0.83
     VIDEOS
    0.73
     differently
    0.69
     angles
    0.64
     Compass
    0.63
    flame
    0.63
     fins
    0.62
     afar
    0.62
    Activations Density 0.182%

    No Known Activations