© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 5107
    Prev
    Next
    INDEX
    Explanations

    words related to headwear, specifically hats

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Hat" and its variations, as well as related terms

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

    No Comments

    Negative Logits
    theless
    -1.10
    ngth
    -1.09
    hower
    -0.85
     glutamate
    -0.80
    etheless
    -0.72
    ¥ŀ
    -0.70
    terday
    -0.70
     UNIVERS
    -0.70
     confir
    -0.70
    ĸļ
    -0.69
    POSITIVE LOGITS
    chet
    1.20
    chery
    1.01
    ches
    0.88
    red
    0.85
     Hat
    0.85
    Hat
    0.85
    ched
    0.84
    wig
    0.84
    cher
    0.82
    dar
    0.76
    Activations Density 0.009%

    No Known Activations