© 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. 3-RES-JB
    11. 15138
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "whip"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "whip" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADRA
    -0.81
    Fort
    -0.73
    ccording
    -0.72
    alg
    -0.72
    Merit
    -0.71
     conflic
    -0.71
    DEN
    -0.69
    ulia
    -0.69
    quickShipAvailable
    -0.69
    thia
    -0.69
    POSITIVE LOGITS
     whip
    1.25
     whipping
    1.18
     Whip
    0.93
     whipped
    0.92
    otine
    0.91
     stitch
    0.81
    toe
    0.81
    sticks
    0.73
    boxing
    0.73
    board
    0.73
    Activations Density 0.005%

    No Known Activations