© 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. 4-RES-JB
    11. 22120
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to using force or speed

    oai_token-act-pair · gpt-3.5-turbo

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

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

    No Comments

    Negative Logits
    ADRA
    -0.84
    thia
    -0.80
    itars
    -0.71
    Fort
    -0.70
    alg
    -0.69
    ators
    -0.67
    DEN
    -0.67
    Merit
    -0.67
    quickShipAvailable
    -0.66
    ereo
    -0.66
    POSITIVE LOGITS
     whipping
    1.21
     whip
    1.20
    otine
    0.91
     whipped
    0.90
    sticks
    0.83
     Whip
    0.82
    tails
    0.81
    stick
    0.79
     stitch
    0.78
     cane
    0.75
    Activations Density 0.011%

    No Known Activations