© 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. 2-RES-JB
    11. 12813
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "whisk" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    terms related to whisking and its variations in cooking contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SOURCE
    -0.68
     revolving
    -0.63
    cision
    -0.62
     besie
    -0.61
     Goddess
    -0.60
     Dome
    -0.59
     mediation
    -0.59
    FUL
    -0.56
     PLAN
    -0.56
     personalized
    -0.56
    POSITIVE LOGITS
     whisk
    1.18
    ers
    1.06
    itudinal
    0.93
    ies
    0.92
    er
    0.91
    eenth
    0.91
    ery
    0.90
    ings
    0.90
    zee
    0.89
    ie
    0.88
    Activations Density 0.011%

    No Known Activations