© 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. 3-RES-JB
    11. 12676
    Prev
    Next
    INDEX
    Explanations

    political and ideological terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation that indicates strong emotional statements or conclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ributes
    -0.82
     mosqu
    -0.80
    ovember
    -0.78
    thal
    -0.77
    poke
    -0.76
    odo
    -0.75
    anka
    -0.73
     tyr
    -0.71
     gobl
    -0.71
    ogly
    -0.70
    POSITIVE LOGITS
     Whereas
    1.21
     Flavoring
    1.20
     Therefore
    1.18
     Nevertheless
    1.16
     Moreover
    1.16
     Thus
    1.15
     Accordingly
    1.14
     Hence
    1.14
     Nonetheless
    1.12
     Consequently
    1.11
    Activations Density 1.164%

    No Known Activations