© 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. 17382
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases ending in a full stop

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express feelings or opinions related to personal experiences and social commentary

    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
     volunte
    -0.96
     challeng
    -0.85
     workspace
    -0.79
     localized
    -0.77
     farmland
    -0.77
     enthusi
    -0.77
     facilit
    -0.77
     preliminary
    -0.75
     coordinated
    -0.74
     affordability
    -0.73
    POSITIVE LOGITS
    Anyway
    1.40
     Anyway
    1.32
    His
    1.29
    He
    1.25
    Yet
    1.24
     He
    1.22
    Nevertheless
    1.21
     Worse
    1.18
     Didn
    1.16
     Surely
    1.16
    Activations Density 0.556%

    No Known Activations