© 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. 22865
    Prev
    Next
    INDEX
    Explanations

    information related to historical events, individuals, and activities

    oai_token-act-pair · gpt-3.5-turbo

    historical military and intelligence affiliations

    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
    idium
    -0.80
    CNN
    -0.76
     POLITICO
    -0.73
    display
    -0.72
    answer
    -0.72
    trigger
    -0.71
     Throw
    -0.66
    rium
    -0.66
     WARN
    -0.65
    Leaks
    -0.64
    POSITIVE LOGITS
    Bec
    0.88
    ometime
    0.85
     missionary
    0.84
     streng
    0.84
     apprentices
    0.83
     stint
    0.81
     summers
    0.80
     Married
    0.80
    Grad
    0.78
     befriend
    0.78
    Activations Density 0.596%

    No Known Activations