© 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. 21715
    Prev
    Next
    INDEX
    Explanations

    proper nouns and locations related to wars or battles

    oai_token-act-pair · gpt-3.5-turbo

    specific character names and their affiliations in a narrative context

    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
     DIY
    -0.72
     ballpark
    -0.72
     golf
    -0.72
     BART
    -0.72
     fitness
    -0.71
     CPR
    -0.70
     weekday
    -0.70
     SPORTS
    -0.70
     taped
    -0.70
     booking
    -0.68
    POSITIVE LOGITS
    grim
    1.31
    û
    1.24
    roth
    1.23
    raq
    1.19
    ael
    1.16
    wyn
    1.15
    uin
    1.14
    oran
    1.12
    nir
    1.11
    yr
    1.10
    Activations Density 0.227%

    No Known Activations