© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    information about people and their actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to players and groups in various contexts

    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
    -+
    -0.86
    runtime
    -0.79
    ðĿ
    -0.69
    atever
    -0.66
    igun
    -0.64
    ween
    -0.63
    =~
    -0.63
    issance
    -0.63
    -|
    -0.62
    =-=-
    -0.62
    POSITIVE LOGITS
     even
    1.25
     downright
    1.19
     outright
    1.00
     EVEN
    0.95
    even
    0.87
     simply
    0.84
     may
    0.77
     actually
    0.76
     genuinely
    0.75
     prefer
    0.74
    Activations Density 0.362%

    No Known Activations