© 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. 3-RES-JB
    6. 13145
    Prev
    Next
    INDEX
    Explanations

    phrases related to first-hand experiences

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hand" as part of compound words or phrases

    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
    vell
    -0.80
     tyr
    -0.65
    uni
    -0.63
    urity
    -0.63
     Neigh
    -0.60
     breach
    -0.60
    aturday
    -0.57
     tremend
    -0.56
    Sphere
    -0.56
     Bravo
    -0.55
    POSITIVE LOGITS
    shake
    0.95
    lers
    0.87
    maid
    0.87
    ling
    0.81
    hand
    0.80
    ingly
    0.78
    %%%%
    0.76
    held
    0.76
    painted
    0.76
    ories
    0.75
    Activations Density 0.010%

    No Known Activations