© 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. 2-RES-JB
    6. 23907
    Prev
    Next
    INDEX
    Explanations

    instances of the word "gig"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "gig."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.82
    66666666
    -0.68
    Ô
    -0.66
     CONTROL
    -0.65
    ÙIJ
    -0.63
    velt
    -0.62
    tenance
    -0.62
     1886
    -0.61
    jong
    -0.61
     Crom
    -0.60
    POSITIVE LOGITS
    abytes
    1.31
    abyte
    1.24
    apixel
    1.14
     gig
    1.10
     gigs
    0.91
    abit
    0.90
    glers
    0.87
    antically
    0.85
    natureconservancy
    0.80
    entric
    0.76
    Activations Density 0.003%

    No Known Activations