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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 17836
    Prev
    Next
    INDEX
    Explanations

    words related to physical actions involving force or impact

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to physical actions or processes

    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
     [*]
    -0.69
     Yen
    -0.66
     Leilan
    -0.66
     CBI
    -0.62
    åĭ
    -0.61
     Nem
    -0.59
     USC
    -0.59
    DragonMagazine
    -0.57
     SAR
    -0.56
     Hermes
    -0.55
    POSITIVE LOGITS
    waukee
    0.97
    emonic
    0.89
    ographed
    0.87
    ochond
    0.85
    aukee
    0.83
    achusetts
    0.83
    ogi
    0.80
    omatic
    0.79
    imore
    0.76
    gage
    0.74
    Activations Density 0.088%

    No Known Activations