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. 17260
    Prev
    Next
    INDEX
    Explanations

    mentions of skilled labor or craftsmanship

    oai_token-act-pair · gpt-3.5-turbo

    terms related to craftsmanship and craft-related activities

    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
    aneously
    -0.79
     Lans
    -0.77
     Peel
    -0.72
     Addiction
    -0.71
     Fare
    -0.70
     Patient
    -0.70
    iance
    -0.68
    othal
    -0.67
     Niagara
    -0.67
     Asset
    -0.66
    POSITIVE LOGITS
     crafts
    1.18
    men
    1.16
    woman
    1.10
    man
    1.10
    mann
    0.92
    worker
    0.85
     laborers
    0.82
    merce
    0.82
    rer
    0.82
    spe
    0.82
    Activations Density 0.030%

    No Known Activations