© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18468
    Prev
    Next
    INDEX
    Explanations

    instances of the word "variant" or "variation"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to variations or alternative forms of concepts or objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.76
    ¯¯
    -0.74
    Ķ
    -0.73
    lins
    -0.71
    uster
    -0.68
    zik
    -0.66
    yer
    -0.66
    cept
    -0.65
    stra
    -0.65
    shire
    -0.64
    POSITIVE LOGITS
    arily
    1.01
     variants
    0.95
     thereof
    0.93
    arios
    0.86
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.85
     allele
    0.84
     variations
    0.81
     variant
    0.79
    iations
    0.75
    atility
    0.75
    Activations Density 0.016%

    No Known Activations