© 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. 4-RES-JB
    11. 16162
    Prev
    Next
    INDEX
    Explanations

    the word "wrap" or variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wrap" and its variations, indicating a focus on the concept of wrapping or enclosing

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

    No Comments

    Negative Logits
    rade
    -0.72
    orie
    -0.71
    oi
    -0.67
    avanaugh
    -0.67
     Lonely
    -0.66
    cca
    -0.65
    relevant
    -0.65
    sych
    -0.65
    yton
    -0.64
    lda
    -0.61
    POSITIVE LOGITS
     wrap
    1.11
    wrap
    1.03
     wrapping
    1.00
     wrapped
    0.99
    adoes
    0.98
     Wrap
    0.93
     wraps
    0.87
     shroud
    0.84
    wra
    0.75
    krit
    0.74
    Activations Density 0.016%

    No Known Activations