© 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. 14019
    Prev
    Next
    INDEX
    Explanations

    keywords related to user intent, especially those indicating a desire or intention

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing desire or intention

    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
    anches
    -0.73
    ioxide
    -0.60
    avia
    -0.57
    BuyableInstoreAndOnline
    -0.57
     showers
    -0.56
    ikarp
    -0.55
    rir
    -0.55
     preparations
    -0.53
    icist
    -0.52
     Tanz
    -0.52
    POSITIVE LOGITS
     to
    0.94
     done
    0.80
     replaced
    0.79
    reprene
    0.78
     undone
    0.77
     answered
    0.75
     pinned
    0.75
     executed
    0.74
     implemented
    0.74
     anyways
    0.73
    Activations Density 0.062%

    No Known Activations