© 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 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. 1725
    Prev
    Next
    INDEX
    Explanations

    references to alternative options or additional possibilities

    oai_token-act-pair · gpt-3.5-turbo

    references to alternative options or entities

    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
    utenant
    -0.74
    ony
    -0.67
    opus
    -0.65
     ç¥ŀ
    -0.65
    cape
    -0.64
    zai
    -0.62
    ouf
    -0.61
     1915
    -0.61
    aban
    -0.61
     EVEN
    -0.61
    POSITIVE LOGITS
    worldly
    2.02
     kinds
    1.08
     aspects
    1.05
     countries
    1.04
     types
    0.99
     avenues
    0.99
     factors
    0.99
     forms
    0.95
     continents
    0.94
    wise
    0.93
    Activations Density 0.108%

    No Known Activations