© 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. 7305
    Prev
    Next
    INDEX
    Explanations

    phrases related to shoes and footwear

    oai_token-act-pair · gpt-3.5-turbo

    words that are variations of "oes" or sound similar to it, indicating a focus on a specific sound pattern in the text

    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
    DERR
    -0.74
    icago
    -0.69
    rade
    -0.66
    rad
    -0.63
    Miller
    -0.60
    SPEC
    -0.60
    rollers
    -0.60
    enton
    -0.60
    èª
    -0.60
     newsp
    -0.59
    POSITIVE LOGITS
    hler
    0.94
    velt
    0.91
    lihood
    0.90
    utenant
    0.85
    oes
    0.84
    ophy
    0.84
    hl
    0.80
    ument
    0.79
    vre
    0.78
    asures
    0.76
    Activations Density 0.011%

    No Known Activations