© 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. 4-RES-JB
    6. 16049
    Prev
    Next
    INDEX
    Explanations

    phrases related to causality or transition in time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "heel" and its variations

    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
    edia
    -0.76
    abilia
    -0.73
    untu
    -0.72
    ucle
    -0.71
    ally
    -0.70
    tein
    -0.69
    MSN
    -0.69
    ishable
    -0.66
    uld
    -0.65
     Sabha
    -0.64
    POSITIVE LOGITS
     heels
    1.41
     heel
    0.97
    toe
    0.83
    lash
    0.81
    butt
    0.77
     feet
    0.77
     elbows
    0.76
    footed
    0.76
     toes
    0.75
     footsteps
    0.75
    Activations Density 0.008%

    No Known Activations