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. 18812
    Prev
    Next
    INDEX
    Explanations

    lists or sequences of items or ingredients

    oai_token-act-pair · gpt-3.5-turbo

    terms related to chemical elements and minerals

    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
     Shutdown
    -0.74
     Cache
    -0.73
    Progress
    -0.72
    hirt
    -0.71
     Booth
    -0.69
    shut
    -0.69
    PsyNetMessage
    -0.68
    progress
    -0.68
     Accountability
    -0.68
     Attend
    -0.68
    POSITIVE LOGITS
     varieties
    1.65
     styles
    1.47
     types
    1.47
     flavors
    1.44
     flavours
    1.41
     herbs
    1.40
     shapes
    1.35
     colors
    1.33
     spices
    1.33
     ingredients
    1.32
    Activations Density 0.415%

    No Known Activations