Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 1884
    Prev
    Next
    INDEX
    Explanations

    words related to tasks or activities that require physical effort or organization

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of choreographed performances and tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Civic
    -0.69
     Milton
    -0.68
    berman
    -0.67
    achev
    -0.65
     parole
    -0.64
    blank
    -0.63
    eem
    -0.62
     Conservatives
    -0.62
     bye
    -0.61
    Honest
    -0.61
    POSITIVE LOGITS
    ographed
    1.43
     chore
    1.40
    ograp
    1.06
    ograph
    0.94
    ographer
    0.94
    icular
    0.91
     gymn
    0.85
    ographs
    0.83
    ographers
    0.83
    ography
    0.82
    Activations Density 0.009%

    No Known Activations