© 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. 4-RES-JB
    11. 15447
    Prev
    Next
    INDEX
    Explanations

    words related to skills or capabilities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "ability" related to various contexts

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

    No Comments

    Negative Logits
    erva
    -0.82
    ergy
    -0.77
    inas
    -0.70
    Ing
    -0.70
    inis
    -0.69
    ften
    -0.65
    stad
    -0.63
    raining
    -0.63
    ERC
    -0.62
    ewski
    -0.62
    POSITIVE LOGITS
    worthiness
    0.98
    ability
    0.94
    itaire
    0.83
    iqueness
    0.80
    ulnerability
    0.79
    anship
    0.79
     mismatch
    0.77
    idad
    0.77
    acies
    0.76
     Pwr
    0.76
    Activations Density 0.016%

    No Known Activations