© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 4902
    Prev
    Next
    INDEX
    Explanations

    mentions of clothing items, specifically 'suits'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of suits or clothing items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sequest
    -0.70
    raltar
    -0.67
     aborted
    -0.67
    lder
    -0.66
     WARN
    -0.63
    udeau
    -0.63
    apo
    -0.63
    INFO
    -0.62
    osate
    -0.61
     Roads
    -0.58
    POSITIVE LOGITS
    suit
    1.40
     suit
    1.38
     suits
    1.37
    suits
    1.30
    cases
    1.28
     Suit
    1.13
    ability
    1.12
    uit
    1.04
    ably
    1.01
    emate
    0.85
    Activations Density 0.010%

    No Known Activations