© 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. 20981
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names starting with a capital letter

    oai_token-act-pair · gpt-3.5-turbo

    elements related to rankings and hierarchical positions

    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
    γ
    -0.82
    avan
    -0.80
     interf
    -0.72
    react
    -0.71
    auga
    -0.69
    displayText
    -0.69
    iaz
    -0.69
    storms
    -0.67
    hran
    -0.66
    anol
    -0.65
    POSITIVE LOGITS
     Top
    2.04
     top
    1.87
     TOP
    1.82
    Top
    1.76
    TOP
    1.65
     ranking
    1.62
    top
    1.62
     ranked
    1.59
     Bottom
    1.53
     rankings
    1.50
    Activations Density 0.253%

    No Known Activations