© 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 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. 9-RES-JB
    11. 2221
    Prev
    Next
    INDEX
    Explanations

    phrases related to questioning or challenging actions or decisions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flow
    -0.75
     wildlife
    -0.74
     daily
    -0.73
     clin
    -0.73
     retreat
    -0.70
     millenn
    -0.70
     intensive
    -0.68
     lodge
    -0.68
     Mahjong
    -0.67
     outpatient
    -0.67
    POSITIVE LOGITS
    although
    1.82
    especially
    1.80
    albeit
    1.70
    except
    1.70
    though
    1.69
    including
    1.69
    unless
    1.68
    which
    1.66
    particularly
    1.64
    perhaps
    1.62
    Activations Density 0.141%

    No Known Activations