© 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. 7-RES-JB
    11. 23624
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases starting with certain special characters followed by words or phrases related to statements or allegations

    oai_token-act-pair · gpt-3.5-turbo

    dialogue or quotes within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minus
    -0.67
     steroids
    -0.66
    lled
    -0.65
     Thornton
    -0.64
     Hai
    -0.63
     derby
    -0.62
     bot
    -0.62
    abouts
    -0.61
     territ
    -0.61
    orate
    -0.60
    POSITIVE LOGITS
    "âĢ¦
    0.99
    "...
    0.97
    ³³³³³³³³
    0.96
    ³³³³³³³³³³³³³³³³
    0.89
    enegger
    0.87
    "[
    0.86
    Congratulations
    0.84
    Today
    0.83
    ...]
    0.82
    Our
    0.82
    Activations Density 0.087%

    No Known Activations