© 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. 3160
    Prev
    Next
    INDEX
    Explanations

    mentions of people or groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or individuals and their experiences

    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
    forth
    -0.68
     Buckley
    -0.64
    Rober
    -0.64
    rang
    -0.62
     Brom
    -0.60
    å§
    -0.60
     JFK
    -0.58
    rich
    -0.57
     Reilly
    -0.57
     Ranger
    -0.56
    POSITIVE LOGITS
    cius
    0.87
    aurus
    0.81
     largeDownload
    0.76
    oft
    0.76
    aunders
    0.73
     =>
    0.70
     ·
    0.69
    cellaneous
    0.66
    wat
    0.66
    hare
    0.66
    Activations Density 0.088%

    No Known Activations