© 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. 8-RES-JB
    11. 6553
    Prev
    Next
    INDEX
    Explanations

    mentions of soy-related products and ingredients

    oai_token-act-pair · gpt-3.5-turbo

    mentions of soy products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hani
    -0.73
    */(
    -0.72
     CBI
    -0.68
    UTERS
    -0.66
    istically
    -0.65
     ESC
    -0.65
     Imran
    -0.65
    cffffcc
    -0.65
     Humanity
    -0.63
     Anonymous
    -0.62
    POSITIVE LOGITS
    bean
    1.70
    beans
    1.68
    bowl
    1.08
    food
    0.97
    lda
    0.92
    atown
    0.90
    char
    0.85
    oken
    0.85
    wu
    0.84
    eah
    0.83
    Activations Density 0.032%

    No Known Activations