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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 7-RES-JB
    6. 14960
    Prev
    Next
    INDEX
    Explanations

    words related to physical exertion and perspiration

    oai_token-act-pair · gpt-3.5-turbo

    references to sweat and sweating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ities
    -0.78
    LY
    -0.71
    ally
    -0.70
    osite
    -0.68
    edly
    -0.67
    lishes
    -0.66
    ********
    -0.65
     Encounter
    -0.65
    -+-+
    -0.65
    ĺħ
    -0.65
    POSITIVE LOGITS
    hirt
    1.25
    pants
    1.21
     sweat
    0.92
     glands
    0.85
    suit
    0.82
    tops
    0.77
    tub
    0.76
    bands
    0.76
     sweats
    0.76
    pees
    0.75
    Activations Density 0.048%

    No Known Activations