© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1011
    Prev
    Next
    INDEX
    Explanations

    words related to specific entities or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific organizations, locations, or entities

    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
     accompanying
    -0.59
     characteristic
    -0.59
    enegger
    -0.59
     combination
    -0.58
     liar
    -0.58
     omission
    -0.58
     dummy
    -0.57
     substitute
    -0.56
     compliment
    -0.56
     negotiator
    -0.55
    POSITIVE LOGITS
    Fest
    0.90
    opolis
    0.83
    adelphia
    0.81
    erville
    0.77
    topia
    0.76
    City
    0.75
    endale
    0.73
    ipedia
    0.72
    Wiki
    0.72
    Aren
    0.72
    Activations Density 0.668%

    No Known Activations