© 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. 11-RES-JB
    11. 9376
    Prev
    Next
    INDEX
    Explanations

    locations or organizations and associated individuals in historical contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a person or entity's noteworthy status or affiliation

    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
    anse
    -0.73
    é¾
    -0.70
     thereof
    -0.69
    è£ħ
    -0.68
    hazard
    -0.68
    trap
    -0.66
    inventoryQuantity
    -0.65
    complex
    -0.64
    .............
    -0.63
    Unique
    -0.63
    POSITIVE LOGITS
     founders
    1.36
     pioneers
    1.27
     architects
    1.20
     earliest
    1.11
     brightest
    1.10
     organizers
    1.10
     few
    1.07
     wealthiest
    1.06
     principals
    1.05
     smartest
    1.05
    Activations Density 0.100%

    No Known Activations