© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20717
    Prev
    Next
    INDEX
    Explanations

    quotations

    oai_token-act-pair · gpt-3.5-turbo

    the word "said" and its variations in reported speech

    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
    tumblr
    -0.82
    Pont
    -0.80
    ãĥ¯ãĥ³
    -0.72
    ãĥİ
    -0.71
    otype
    -0.71
    Untitled
    -0.70
    à¦
    -0.69
    Lens
    -0.69
    cept
    -0.69
    joice
    -0.69
    POSITIVE LOGITS
    :"
    0.76
     moreover
    0.75
     secondly
    0.73
     furthermore
    0.72
     Hancock
    0.69
     afterward
    0.67
     goodbye
    0.67
     anecd
    0.66
     pauses
    0.66
     aides
    0.65
    Activations Density 0.157%

    No Known Activations