© 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. 1-RES-JB
    11. 9470
    Prev
    Next
    INDEX
    Explanations

    the word "precisely" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    the word "precisely" and its variations indicating exactness or specificity

    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
    oa
    -0.74
    ned
    -0.69
    abies
    -0.66
    asta
    -0.64
    Reviewer
    -0.63
    TRY
    -0.63
    ocene
    -0.62
    rug
    -0.62
     BYU
    -0.61
    nee
    -0.61
    POSITIVE LOGITS
     precisely
    0.90
    uracy
    0.85
    £ı
    0.83
    cise
    0.82
     guiActiveUn
    0.78
    initions
    0.78
     deline
    0.77
     pinpoint
    0.77
    entimes
    0.76
    ustomed
    0.74
    Activations Density 0.003%

    No Known Activations