© 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. 0-RES-JB
    11. 18023
    Prev
    Next
    INDEX
    Explanations

    words related to the casino game "roulette"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "roulette."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ACT
    -0.73
     native
    -0.73
     Abstract
    -0.63
     static
    -0.63
     typ
    -0.63
     early
    -0.59
     upt
    -0.59
    apsed
    -0.59
     dead
    -0.58
    UR
    -0.57
    POSITIVE LOGITS
    lette
    4.66
    lete
    1.59
    let
    1.46
    lets
    1.39
    lett
    1.38
    rette
    1.37
    ttes
    1.30
    letes
    1.23
    LET
    1.21
    lda
    1.08
    Activations Density 0.015%

    No Known Activations