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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9194
    Prev
    Next
    INDEX
    Explanations

    ranges between quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to populations and quantities

    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
     trave
    -0.54
     constitu
    -0.53
    PRO
    -0.53
     Secondly
    -0.51
     enthusi
    -0.49
    parent
    -0.48
    ESE
    -0.48
     destro
    -0.48
    pring
    -0.47
    AME
    -0.47
    POSITIVE LOGITS
     fewer
    1.27
     less
    1.16
     just
    1.14
     only
    1.06
     merely
    0.96
     mere
    0.95
     barely
    0.92
     around
    0.89
     about
    0.87
     roughly
    0.86
    Activations Density 0.407%

    No Known Activations