© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 17264
    Prev
    Next
    INDEX
    Explanations

    words related to skill, proficiency, expertise, and adeptness

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate skill or proficiency in various abilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´
    -0.69
    ndum
    -0.67
    ylum
    -0.66
    izons
    -0.65
    idium
    -0.62
    hea
    -0.62
    pta
    -0.61
     Concern
    -0.61
    Ru
    -0.61
    udeb
    -0.61
    POSITIVE LOGITS
     tact
    1.03
     manip
    1.02
     negotiator
    0.98
     improvis
    0.93
     navig
    0.90
     swords
    0.88
     crafts
    0.88
     adept
    0.88
     handling
    0.88
     pian
    0.85
    Activations Density 0.216%

    No Known Activations