Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 14275
    Prev
    Next
    INDEX
    Explanations

    food and drink items

    oai_token-act-pair · gpt-3.5-turbo

    brand names or specific product types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     broadcasting
    -0.91
     announ
    -0.89
     strateg
    -0.87
     recru
    -0.86
     broadcasters
    -0.86
    entry
    -0.85
     coordin
    -0.85
     programmers
    -0.83
     referees
    -0.83
     employers
    -0.83
    POSITIVE LOGITS
     Cream
    1.44
     Chocolate
    1.41
     Sauce
    1.38
     Blend
    1.38
     Cinnamon
    1.37
     Powder
    1.35
     Spice
    1.32
     Rye
    1.31
     Lime
    1.30
     Vanilla
    1.30
    Activations Density 0.207%

    No Known Activations