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. 1-RES-JB
    6. 16459
    Prev
    Next
    INDEX
    Explanations

    mentions of physical characteristics or actions related to cleanliness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "cle," indicating a focus on clarity or clearness

    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
     Tul
    -0.78
     Krug
    -0.71
     Kop
    -0.70
     Galaxy
    -0.69
     Paramount
    -0.67
     Tens
    -0.66
     Kings
    -0.65
     Berk
    -0.64
     Physicians
    -0.64
     Trafford
    -0.64
    POSITIVE LOGITS
     cle
    1.18
    arest
    1.04
    combe
    0.91
    avage
    0.90
    ogly
    0.85
    bage
    0.80
    arms
    0.77
    fruit
    0.76
    utic
    0.76
    zie
    0.73
    Activations Density 0.002%

    No Known Activations