© 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. 13465
    Prev
    Next
    INDEX
    Explanations

    the word "vers" followed by a digit (usually 9 or 10)

    oai_token-act-pair · gpt-3.5-turbo

    words that relate to various forms of "versus" comparisons or contrasts

    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
    opathic
    -0.66
     interior
    -0.64
    ŃĶ
    -0.64
     impulse
    -0.64
    ľ
    -0.63
     customary
    -0.62
     creeping
    -0.62
     protective
    -0.61
     mould
    -0.61
     pre
    -0.60
    POSITIVE LOGITS
    vers
    1.23
    theless
    1.08
    atility
    1.06
    hip
    0.94
    olver
    0.92
    atile
    0.91
    Vers
    0.89
    chool
    0.88
    erver
    0.86
    vous
    0.85
    Activations Density 0.006%

    No Known Activations