© 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. 2-RES-JB
    11. 7878
    Prev
    Next
    INDEX
    Explanations

    mentions of activities related to physical movement or performance, particularly dance-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to choreography and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berman
    -0.71
     Civic
    -0.70
     Milton
    -0.67
    eem
    -0.63
     Conservatives
    -0.61
     Citizens
    -0.61
     Sherman
    -0.60
    reens
    -0.60
     Enterprise
    -0.60
     Governments
    -0.60
    POSITIVE LOGITS
    ographed
    1.41
     chore
    1.27
    ograp
    1.04
    ograph
    0.99
    ographer
    0.97
    icular
    0.92
    ographs
    0.89
    ography
    0.84
     gymn
    0.84
    ographers
    0.83
    Activations Density 0.011%

    No Known Activations