© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 1708
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or initiative

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "stepped."

    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
     Abstract
    -0.64
     avail
    -0.64
     trad
    -0.60
     Contains
    -0.59
    atu
    -0.59
     Indians
    -0.59
    rx
    -0.59
    icle
    -0.59
    itutes
    -0.58
     attachments
    -0.58
    POSITIVE LOGITS
     stepped
    3.36
     stepping
    1.89
     steps
    1.46
     step
    1.43
     walked
    1.41
     intervened
    1.38
    steps
    1.29
     leapt
    1.28
     stood
    1.25
     tightened
    1.24
    Activations Density 0.011%

    No Known Activations