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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14077
    Prev
    Next
    INDEX
    Explanations

    key terms related to racing and competition

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic concepts and job market dynamics

    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
    ãĢ
    -0.73
    ³³³³
    -0.72
    *:
    -0.71
     âĢ
    -0.70
    :-
    -0.68
     âĺ
    -0.66
    *)
    -0.66
    ::::
    -0.66
    îĢ
    -0.66
    ³³³
    -0.65
    POSITIVE LOGITS
     and
    0.98
     or
    0.85
     instead
    0.72
     outwe
    0.67
    afer
    0.64
     apiece
    0.63
     etc
    0.62
     afterward
    0.61
     versus
    0.61
     healthier
    0.60
    Activations Density 1.072%

    No Known Activations