© 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. 11-RES-JB
    11. 18557
    Prev
    Next
    INDEX
    Explanations

    keywords related to academic books and publications

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to identity and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pumps
    -0.84
     tether
    -0.83
     slightest
    -0.82
     allowances
    -0.82
     exhib
    -0.82
     piston
    -0.81
     importantly
    -0.81
     strap
    -0.80
     inhibitor
    -0.80
     bolt
    -0.79
    POSITIVE LOGITS
     Excellence
    1.44
     Politics
    1.44
     Terrorism
    1.42
     Violence
    1.40
     Contemporary
    1.39
     Journalism
    1.37
     Childhood
    1.37
     Everyday
    1.36
     Conflict
    1.36
     Culture
    1.35
    Activations Density 0.198%

    No Known Activations