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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 2895
    Prev
    Next
    INDEX
    Explanations

    words related to swinging or movement back and forth

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "swing" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ère
    -0.80
    Documents
    -0.78
     CODE
    -0.69
     Meth
    -0.68
    Reviewed
    -0.67
    Doctor
    -0.67
     certs
    -0.67
    ĨĴ
    -0.67
    NASA
    -0.66
     colonization
    -0.66
    POSITIVE LOGITS
     swing
    3.95
     Swing
    2.60
    swing
    2.58
     swings
    2.44
     swinging
    2.14
     swung
    2.08
     tilt
    1.32
     bounce
    1.28
     battleground
    1.19
     sway
    1.17
    Activations Density 0.021%

    No Known Activations