© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7784
    Prev
    Next
    INDEX
    Explanations

    instances of the word "twice" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "twice" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UME
    -0.77
    ERAL
    -0.72
    Reviewer
    -0.71
    ogi
    -0.70
    andr
    -0.70
    AMI
    -0.69
    olve
    -0.69
    orge
    -0.68
    ettle
    -0.68
    oes
    -0.66
    POSITIVE LOGITS
     consecut
    0.94
    theless
    0.89
    fold
    0.73
     apiece
    0.71
     dipping
    0.70
     dozen
    0.68
     thirds
    0.67
    fif
    0.66
     consecutive
    0.65
     halves
    0.64
    Activations Density 0.023%

    No Known Activations