© 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. 0-RES-JB
    6. 19198
    Prev
    Next
    INDEX
    Explanations

    information or snippets related to various situations, possibly from news articles or reports

    oai_token-act-pair · gpt-3.5-turbo

    instances of specific symbols or punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inputs
    -0.64
    ãĥĥãĤ¯
    -0.58
    orc
    -0.58
    OA
    -0.57
    Hy
    -0.57
    augh
    -0.57
    oyal
    -0.56
    ammy
    -0.55
     Orb
    -0.54
    chem
    -0.54
    POSITIVE LOGITS
     [...]
    3.82
     [â̦]
    3.77
    â̦]
    2.12
    ".[
    1.96
    ...]
    1.93
    SPONSORED
    1.66
     [/
    1.52
    ."[
    1.51
     âĢİ
    1.50
     ..."
    1.47
    Activations Density 0.006%

    No Known Activations