© 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. 1-RES-JB
    11. 10226
    Prev
    Next
    INDEX
    Explanations

    locations and dates

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas and periods

    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
    ensor
    -0.65
    erence
    -0.64
    qv
    -0.59
    vation
    -0.59
    INAL
    -0.57
    athered
    -0.56
    iku
    -0.55
    escription
    -0.53
    erent
    -0.53
    uit
    -0.53
    POSITIVE LOGITS
    76561
    0.81
     etc
    0.64
     Kinnikuman
    0.59
     aka
    0.56
    åĮ
    0.54
     including
    0.52
     citing
    0.52
     Ltd
    0.51
    ktop
    0.50
     Calif
    0.50
    Activations Density 1.445%

    No Known Activations