Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10912
    Prev
    Next
    INDEX
    Explanations

    words related to digging or burying

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "burrow."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MFT
    -0.66
     outsourcing
    -0.63
     Bard
    -0.61
     Eye
    -0.60
     uncomp
    -0.59
     Eclipse
    -0.59
    opathy
    -0.58
    enza
    -0.57
     dressing
    -0.57
     Aux
    -0.57
    POSITIVE LOGITS
    rowing
    1.35
    pees
    1.31
    geon
    1.30
    rito
    1.30
    row
    1.28
    rows
    1.24
    bling
    1.19
    geoning
    1.18
    lap
    1.15
    rit
    1.15
    Activations Density 0.030%

    No Known Activations