© 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. 19793
    Prev
    Next
    INDEX
    Explanations

    personal descriptions or evaluations of individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong positive sentiments and descriptions of excellence in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    OPLE
    -0.85
    enter
    -0.79
    threat
    -0.69
    inyl
    -0.68
    ogenesis
    -0.68
    Reward
    -0.67
     Supplemental
    -0.67
    ="#
    -0.67
    Solution
    -0.64
    ocation
    -0.64
    POSITIVE LOGITS
     underrated
    1.45
     amazing
    1.39
     fantastic
    1.37
     excellent
    1.33
     awesome
    1.29
     phenomenal
    1.27
     wonderfully
    1.27
     wonderful
    1.25
     amazingly
    1.25
     gorgeous
    1.24
    Activations Density 0.785%

    No Known Activations