© 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. 20302
    Prev
    Next
    INDEX
    Explanations

    expressions related to commitment and dedication

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of commitment or dedication

    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
    DragonMagazine
    -1.14
    ults
    -0.79
    igmatic
    -0.77
    ratulations
    -0.72
    llo
    -0.71
    æĺ
    -0.70
    redits
    -0.69
    ooked
    -0.65
    nette
    -0.65
    alde
    -0.64
    POSITIVE LOGITS
     preserving
    1.40
     ensuring
    1.36
     maintaining
    1.32
     upholding
    1.32
     protecting
    1.29
     improving
    1.18
     achieving
    1.18
     keeping
    1.15
     helping
    1.14
     providing
    1.12
    Activations Density 0.087%

    No Known Activations