© 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. 2702
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of salads

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of salads

    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
    redit
    -0.85
    asters
    -0.78
    aken
    -0.78
    venants
    -0.72
    err
    -0.71
    ör
    -0.71
    ilings
    -0.66
    obil
    -0.66
    runner
    -0.66
    shock
    -0.65
    POSITIVE LOGITS
    ashtra
    0.91
     greens
    0.80
    IUM
    0.75
     dressing
    0.75
    LINE
    0.73
     salad
    0.70
     garden
    0.70
    seed
    0.69
    yard
    0.69
     supper
    0.68
    Activations Density 0.110%

    No Known Activations