© 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. 10490
    Prev
    Next
    INDEX
    Explanations

    the word "again"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "agin" and related 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
    ding
    -0.78
    iffe
    -0.75
    theless
    -0.69
    fax
    -0.66
    jar
    -0.66
    header
    -0.66
    grading
    -0.64
    fer
    -0.64
    izen
    -0.63
    ded
    -0.63
    POSITIVE LOGITS
    amus
    1.12
    agin
    0.89
    uments
    0.89
    ================================================================
    0.85
    azine
    0.80
    entials
    0.78
    ement
    0.76
    aceae
    0.76
    insula
    0.76
    amaz
    0.76
    Activations Density 0.031%

    No Known Activations