© 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. 10-RES-JB
    11. 13928
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns commonly used when describing actions related to accusations or blame

    oai_token-act-pair · gpt-3.5-turbo

    references to accusations or claims against individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOR
    -0.65
    endor
    -0.64
    WOR
    -0.55
    nov
    -0.53
    atform
    -0.52
     Brav
    -0.52
     adolesc
    -0.52
    nan
    -0.52
     Cowboy
    -0.51
    iants
    -0.51
    POSITIVE LOGITS
     of
    1.28
    of
    1.27
     thereof
    1.06
    Of
    1.05
     Of
    0.95
    OF
    0.92
     OF
    0.87
    ta
    0.72
    ensor
    0.65
    oft
    0.62
    Activations Density 0.360%

    No Known Activations