© 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. 15714
    Prev
    Next
    INDEX
    Explanations

    references to scientific theories

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific theories

    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
    ibaba
    -0.65
    cler
    -0.62
    ienced
    -0.60
    iencies
    -0.59
    Interstitial
    -0.58
    æĸ¹
    -0.58
     Mous
    -0.57
     Pradesh
    -0.57
    ãģį
    -0.57
    Numbers
    -0.57
    POSITIVE LOGITS
    icist
    1.28
     underpin
    1.01
    sonian
    0.98
     theories
    0.98
     predicts
    0.97
     theor
    0.93
    ologies
    0.93
     hypothes
    0.90
     formulated
    0.88
     predicting
    0.87
    Activations Density 0.048%

    No Known Activations