© 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. 7-RES-JB
    11. 6473
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of vegetables

    oai_token-act-pair · gpt-3.5-turbo

    mentions of vegetables and their varieties or preparations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dinand
    -0.87
    raints
    -0.74
    administ
    -0.72
    DOS
    -0.70
    communications
    -0.70
    oning
    -0.69
    ebin
    -0.68
    Oracle
    -0.68
    interstitial
    -0.68
    mberg
    -0.67
    POSITIVE LOGITS
     vegetables
    0.99
     garden
    0.96
     vegetable
    0.96
     peel
    0.91
     gardens
    0.90
     Garden
    0.89
     soup
    0.88
    bush
    0.88
     salad
    0.86
     juices
    0.85
    Activations Density 0.029%

    No Known Activations