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

    Neuronpedia

    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. 11-RES-JB
    11. 1466
    Prev
    Next
    INDEX
    Explanations

    negative statements connoting rejection or dismissal

    oai_token-act-pair · gpt-3.5-turbo

    negations and evaluations of options or ideas

    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
    ĸļ
    -0.77
    hua
    -0.72
     transcript
    -0.71
    reader
    -0.67
     Citation
    -0.67
     annotations
    -0.66
     Reporting
    -0.66
     handwritten
    -0.65
    ibel
    -0.63
     quotations
    -0.62
    POSITIVE LOGITS
     feasible
    1.47
    thinkable
    1.19
     viable
    1.16
     impractical
    1.12
     feas
    1.07
     preferable
    1.07
     advisable
    1.07
     desirable
    1.03
     achievable
    1.03
     practicable
    1.02
    Activations Density 0.354%

    No Known Activations