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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5011
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "belt"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "belt"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [_
    -0.76
    adow
    -0.66
    reens
    -0.65
    photos
    -0.64
    Psych
    -0.64
    Journal
    -0.62
     Likes
    -0.61
     Representatives
    -0.61
    Capt
    -0.60
    SCP
    -0.60
    POSITIVE LOGITS
     belt
    4.28
     belts
    3.73
    belt
    3.28
     Belt
    2.89
     buckle
    1.50
     strap
    1.36
     holster
    1.32
     collar
    1.22
     necklace
    1.17
     waist
    1.11
    Activations Density 0.022%

    No Known Activations