© 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. 9-RES-JB
    11. 1435
    Prev
    Next
    INDEX
    Explanations

    words related to wheeled vehicles or movement related to wheels

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "wheel"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.73
     Echoes
    -0.65
    inates
    -0.64
    uated
    -0.64
     Carbuncle
    -0.62
     Antiqu
    -0.62
    pmwiki
    -0.62
     Gallery
    -0.61
     Garr
    -0.61
    EMBER
    -0.60
    POSITIVE LOGITS
    eling
    1.30
    esome
    1.14
    riter
    1.05
    lp
    1.04
    ldon
    1.02
    elin
    0.99
    tted
    0.95
    rote
    0.94
    lf
    0.94
    lda
    0.94
    Activations Density 0.042%

    No Known Activations