© 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. 5004
    Prev
    Next
    INDEX
    Explanations

    commonalities or shared characteristics between different entities or groups

    oai_token-act-pair · gpt-3.5-turbo

    segments discussing shared characteristics or commonalities among different groups 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
    lems
    -0.72
    duc
    -0.67
    anish
    -0.65
    astic
    -0.65
     Secondly
    -0.64
    hift
    -0.63
     outwe
    -0.63
    astics
    -0.63
    vernment
    -0.61
    enth
    -0.61
    POSITIVE LOGITS
     similarities
    1.11
     common
    1.04
    same
    0.98
     similarity
    0.96
     characteristics
    0.93
     similar
    0.93
     ancestry
    0.91
     resemblance
    0.89
     traits
    0.86
     ancestor
    0.85
    Activations Density 0.091%

    No Known Activations