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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2-RES-JB
    6. 16957
    Prev
    Next
    INDEX
    Explanations

    words related to clothing items, specifically suits

    oai_token-act-pair · gpt-3.5-turbo

    references to suits, particularly formal clothing or legal terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.68
    apo
    -0.65
    osate
    -0.65
    prototype
    -0.62
    INFO
    -0.62
    rolet
    -0.61
    ulhu
    -0.61
    udeau
    -0.60
     sequest
    -0.60
    lder
    -0.58
    POSITIVE LOGITS
    suit
    1.27
    cases
    1.19
    ably
    1.12
     suits
    1.12
    suits
    1.07
    ability
    1.06
     suit
    1.06
    uit
    0.92
     jacket
    0.86
    aments
    0.85
    Activations Density 0.008%

    No Known Activations