© 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. 1-RES-JB
    6. 7229
    Prev
    Next
    INDEX
    Explanations

    commands or instructions in a technical context

    oai_token-act-pair · gpt-3.5-turbo

    clauses that begin with "If you" indicating conditional scenarios or instructions

    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
    bars
    -0.81
    bar
    -0.75
    pit
    -0.74
    rod
    -0.74
    far
    -0.73
    cre
    -0.72
    bill
    -0.71
    ylum
    -0.70
    dev
    -0.69
    weed
    -0.68
    POSITIVE LOGITS
     optionally
    1.03
    awaru
    1.02
    ++++++++
    0.86
     simplify
    0.80
    ichever
    0.78
     guessed
    0.78
    yip
    0.78
    ++++
    0.78
    gencies
    0.77
    theless
    0.76
    Activations Density 0.930%

    No Known Activations