© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 12728
    Prev
    Next
    INDEX
    Explanations

    mentions of the ability or potential to complete a specific action or task

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive "to" as part of various phrases or actions

    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
    irlf
    -0.66
    retty
    -0.63
    ividual
    -0.63
    izoph
    -0.62
    nesota
    -0.61
    ecause
    -0.60
    unct
    -0.60
    inav
    -0.59
    ancial
    -0.58
    enegger
    -0.58
    POSITIVE LOGITS
     to
    1.52
    to
    0.99
     thereto
    0.97
     TO
    0.88
    To
    0.83
     towards
    0.81
     toward
    0.81
     unto
    0.77
     To
    0.76
     into
    0.62
    Activations Density 1.094%

    No Known Activations