© 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. 9-RES-JB
    11. 15551
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing contrast or exception

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the word "by" indicating causation or agency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounter
    -0.68
    igi
    -0.68
    halla
    -0.61
    aminer
    -0.60
    hess
    -0.56
     flats
    -0.55
    ptions
    -0.55
    earable
    -0.55
    bian
    -0.54
     Scand
    -0.54
    POSITIVE LOGITS
    products
    1.41
    product
    1.18
     virtue
    1.14
    laws
    1.11
     implication
    1.08
    gone
    1.05
     extension
    1.00
    pass
    0.95
    catch
    0.95
     definition
    0.95
    Activations Density 0.085%

    No Known Activations