© 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. 11498
    Prev
    Next
    INDEX
    Explanations

    references to things that are extensive or thorough

    oai_token-act-pair · gpt-3.5-turbo

    terms related to thoroughness or intensity 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
    fuck
    -0.69
    wake
    -0.67
    luck
    -0.65
     Symbol
    -0.63
    gey
    -0.63
     loser
    -0.63
    uck
    -0.62
    coin
    -0.62
    Tip
    -0.61
    clock
    -0.60
    POSITIVE LOGITS
     extensive
    3.23
     exhaustive
    1.97
     lengthy
    1.66
     expansive
    1.62
     considerable
    1.61
     ample
    1.60
     extensively
    1.56
     elaborate
    1.55
     comprehensive
    1.51
     rigorous
    1.45
    Activations Density 0.009%

    No Known Activations