© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7155
    Prev
    Next
    INDEX
    Explanations

    dates and months

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing uncertainty or lack of knowledge

    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
    osate
    -0.23
    utsu
    -0.19
    hod
    -0.18
    govtrack
    -0.18
    awed
    -0.17
    pas
    -0.17
    tein
    -0.17
     Horus
    -0.17
     Roof
    -0.17
    [/
    -0.17
    POSITIVE LOGITS
     exerc
    0.18
    querque
    0.17
     redesigned
    0.15
     recre
    0.15
     nucleus
    0.15
     wealthier
    0.15
     accessories
    0.15
     continuum
    0.15
     curric
    0.14
     terminology
    0.14
    Activations Density 10.549%

    No Known Activations