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. 14282
    Prev
    Next
    INDEX
    Explanations

    clauses starting with a verb and followed by a comma

    oai_token-act-pair · gpt-3.5-turbo

    punctuations or pauses that separate ideas in sentences

    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
    MAX
    -0.68
    osc
    -0.62
    nih
    -0.58
    ANN
    -0.58
    rand
    -0.56
    untarily
    -0.56
    num
    -0.55
    ocalypse
    -0.55
    TY
    -0.55
    phant
    -0.54
    POSITIVE LOGITS
     meanwhile
    1.41
     however
    1.30
     huh
    1.08
     moreover
    1.02
     alas
    0.93
     unsurprisingly
    0.93
     therefore
    0.90
     albeit
    0.86
     namely
    0.82
     though
    0.81
    Activations Density 0.414%

    No Known Activations