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. 5-RES-JB
    6. 15400
    Prev
    Next
    INDEX
    Explanations

    scientific or medical findings and reports

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to documentation and reporting of observations or findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pin
    -0.66
    awk
    -0.63
    oyal
    -0.62
    fin
    -0.61
     patience
    -0.61
    ospel
    -0.61
     humble
    -0.60
    pat
    -0.60
    cop
    -0.59
    rest
    -0.59
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.78
     psychiat
    0.77
     clinically
    0.76
     anecd
    0.74
     Parenthood
    0.73
     Obj
    0.72
     Qiao
    0.71
     enz
    0.70
     elsewhere
    0.70
     UD
    0.70
    Activations Density 0.174%

    No Known Activations