© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7843
    Prev
    Next
    INDEX
    Explanations

    **phrases indicating determination or commitment to a specific course of action.**

    oai_token-act-pair · gpt-3.5-turbo

    statements involving future intentions or commitments

    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
    UA
    -0.72
    BuyableInstoreAndOnline
    -0.68
    JD
    -0.67
    amps
    -0.67
     Pict
    -0.65
    ENDED
    -0.65
    ãĤ´ãĥ³
    -0.63
     Extras
    -0.63
    URRENT
    -0.61
    hea
    -0.59
    POSITIVE LOGITS
     gladly
    1.42
     NEVER
    1.33
     ALWAYS
    1.27
     inevitably
    1.22
     never
    1.21
     undoubtedly
    1.16
     always
    1.12
     surely
    1.12
    never
    1.12
     doubtless
    1.11
    Activations Density 0.205%

    No Known Activations