© 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. 7069
    Prev
    Next
    INDEX
    Explanations

    academics institutions, particularly universities

    oai_token-act-pair · gpt-3.5-turbo

    sequences of characters that resemble institutional or organizational names, particularly universities

    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
    riv
    -0.69
     IM
    -0.66
    IME
    -0.66
    rete
    -0.66
     XIV
    -0.65
    SI
    -0.65
    missible
    -0.64
     RV
    -0.64
     SV
    -0.63
     SJ
    -0.63
    POSITIVE LOGITS
     Bolivia
    0.80
     Byz
    0.80
     Bahamas
    0.76
    leck
    0.75
     Candle
    0.74
     Bulgarian
    0.74
     Blackwell
    0.73
     Bulgaria
    0.72
     Cao
    0.72
     cannabin
    0.71
    Activations Density 0.163%

    No Known Activations