© 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. 0-RES-JB
    11. 7744
    Prev
    Next
    INDEX
    Explanations

    instances related to tasks or projects being successfully finished

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "complete."

    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
    yang
    -0.75
    roots
    -0.69
    brook
    -0.68
    bors
    -0.65
    isk
    -0.65
    76561
    -0.65
     GOODMAN
    -0.63
    chant
    -0.63
    ector
    -0.62
    aly
    -0.62
    POSITIVE LOGITS
     complete
    3.72
    complete
    2.54
     Complete
    2.02
    Complete
    1.98
     completed
    1.80
     completes
    1.67
     COMPLE
    1.59
     full
    1.48
     completing
    1.38
     incomplete
    1.37
    Activations Density 0.018%

    No Known Activations