© 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. 9-RES-JB
    11. 17080
    Prev
    Next
    INDEX
    Explanations

    keywords related to people's names and positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences involving traumatic events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chuck
    -0.77
     conventions
    -0.70
     Vaugh
    -0.68
     instincts
    -0.66
     increments
    -0.64
     binge
    -0.64
     stale
    -0.64
    undy
    -0.64
     checks
    -0.63
     ponies
    -0.63
    POSITIVE LOGITS
    ÄŁ
    1.28
    oglu
    1.17
    Äĩ
    1.16
    rahim
    1.06
     Sheikh
    1.05
    oÄŁ
    1.01
     Istanbul
    0.98
     Ä
    0.98
     Yose
    0.97
     Kou
    0.97
    Activations Density 0.528%

    No Known Activations