© 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. 1-RES-JB
    11. 3431
    Prev
    Next
    INDEX
    Explanations

    the word "dig" at the end of words

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "ig"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plain
    -0.77
    ervative
    -0.67
     Sussex
    -0.66
     sideline
    -0.62
     Nurs
    -0.61
     Somerset
    -0.60
    WAYS
    -0.60
     Sov
    -0.59
     CSI
    -0.59
     colon
    -0.58
    POSITIVE LOGITS
    rett
    1.11
    abyte
    1.10
    wig
    1.09
    arette
    1.08
    inning
    1.07
    ig
    1.07
    loo
    1.04
    ga
    1.03
    ogo
    1.02
    arettes
    1.02
    Activations Density 0.015%

    No Known Activations