© 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. 2-RES-JB
    11. 13789
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific names or terms, specifically the term "sa" appearing with different activation values

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific location or entity

    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
    starter
    -0.84
    LIN
    -0.82
    lines
    -0.75
    INGTON
    -0.71
    tails
    -0.69
     unaff
    -0.69
    papers
    -0.68
     Chrom
    -0.67
    breaks
    -0.67
     Cavaliers
    -0.65
    POSITIVE LOGITS
    pling
    1.34
    plings
    1.14
    uth
    1.05
    velength
    0.99
    ñ
    0.99
    iety
    0.95
    uthor
    0.95
    ud
    0.95
    asa
    0.93
    isoft
    0.93
    Activations Density 0.003%

    No Known Activations