© 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. 9-RES-JB
    11. 8722
    Prev
    Next
    INDEX
    Explanations

    nouns related to reasons or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reasons or justifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.90
    ratulations
    -0.79
     yourselves
    -0.75
    auld
    -0.74
    vier
    -0.72
    ashtra
    -0.71
    uilt
    -0.70
    acci
    -0.69
    dozen
    -0.66
    };
    -0.65
    POSITIVE LOGITS
     glory
    0.75
    ãĥ¯
    0.66
     persuasion
    0.64
    ãĥĬ
    0.63
    venge
    0.63
     perfection
    0.62
    ãĤ´ãĥ³
    0.62
    ãĤ¨ãĥ«
    0.59
     Notting
    0.58
     activism
    0.58
    Activations Density 0.448%

    No Known Activations