© 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. 272
    Prev
    Next
    INDEX
    Explanations

    numeric representations or symbols within a document

    oai_token-act-pair · gpt-3.5-turbo

    specific symbols or encoded characters in a data format

    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
    bably
    -0.92
    esses
    -0.92
    iences
    -0.88
    itably
    -0.87
    ependence
    -0.83
    bats
    -0.79
    xual
    -0.77
    itionally
    -0.76
    inately
    -0.73
     Hancock
    -0.71
    POSITIVE LOGITS
    CLASSIFIED
    0.73
    ////////////////////////////////
    0.72
    ipedia
    0.69
     undone
    0.66
    dayName
    0.66
    ï¸ı
    0.64
     sclerosis
    0.63
    Flow
    0.62
    Tok
    0.62
    Magikarp
    0.62
    Activations Density 0.067%

    No Known Activations