© 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. 7850
    Prev
    Next
    INDEX
    Explanations

    technical and economic terms related to finance and health

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional intelligence and related metrics

    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
    alter
    -0.68
    went
    -0.67
     redesigned
    -0.67
     anew
    -0.61
    Changed
    -0.60
     rearr
    -0.60
     Kenobi
    -0.57
     remod
    -0.57
     Blueprint
    -0.57
     Clever
    -0.56
    POSITIVE LOGITS
     rates
    1.22
     levels
    1.13
     thresholds
    1.12
     percentages
    1.08
     density
    1.04
     threshold
    1.04
    ensity
    1.04
     (>
    1.01
     rate
    0.99
     Rates
    0.98
    Activations Density 0.174%

    No Known Activations