© 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. 3-RES-JB
    11. 1852
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names ("Whit")

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Whit" or related references

    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
    anwhile
    -0.98
    PsyNetMessage
    -0.91
    igslist
    -0.80
    ournal
    -0.78
    Pg
    -0.75
    ccording
    -0.73
    aeda
    -0.70
    Downloadha
    -0.70
    raltar
    -0.70
     mileage
    -0.68
    POSITIVE LOGITS
    ewater
    1.24
    bread
    1.15
    comb
    1.03
    robe
    1.01
    eness
    1.01
    ney
    0.99
    acre
    0.98
    ners
    0.97
    ening
    0.96
    neys
    0.95
    Activations Density 0.005%

    No Known Activations