© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17263
    Prev
    Next
    INDEX
    Explanations

    information provided by spokespeople in news articles

    oai_token-act-pair · gpt-3.5-turbo

    references to spokespersons or representatives

    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
    rament
    -0.72
    spons
    -0.68
    SPONSORED
    -0.65
    acca
    -0.65
     bearded
    -0.64
    omer
    -0.64
    pan
    -0.63
    aughs
    -0.63
    don
    -0.62
    tein
    -0.62
    POSITIVE LOGITS
     Anne
    1.17
     Marie
    1.10
     Louise
    1.04
     Nicole
    1.00
     Isabel
    0.94
    Anne
    0.94
     Christina
    0.93
     Elizabeth
    0.92
     Elaine
    0.90
     Mary
    0.89
    Activations Density 0.044%

    No Known Activations