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. 11-RES-JB
    6. 3452
    Prev
    Next
    INDEX
    Explanations

    references to specifics related to cooking and kitchen activities, especially involving specific ingredients like walnuts

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dialogue
    -0.71
     Chomsky
    -0.68
     Citation
    -0.67
     Journalists
    -0.64
     Transcript
    -0.64
    Analysis
    -0.63
     Canaver
    -0.63
     Players
    -0.63
    Wiki
    -0.63
    Information
    -0.62
    POSITIVE LOGITS
     freezer
    0.99
     haha
    0.99
     :(
    0.92
     veggies
    0.90
     ðŁĻĤ
    0.89
     fridge
    0.87
     allergies
    0.85
     leftover
    0.85
     lol
    0.84
     ðŁĺ
    0.82
    Activations Density 0.756%

    No Known Activations