© 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. 13916
    Prev
    Next
    INDEX
    Explanations

    personal narratives or accounts

    oai_token-act-pair · gpt-3.5-turbo

    references to children and their experiences

    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
     Citiz
    -0.53
     Marshal
    -0.53
     metic
    -0.52
     Occupations
    -0.52
     Ended
    -0.52
     distingu
    -0.51
    }{
    -0.50
     Instruct
    -0.50
    mean
    -0.50
    usually
    -0.50
    POSITIVE LOGITS
    azeera
    0.62
     refunds
    0.60
    xit
    0.60
     regrets
    0.57
     boycot
    0.56
    ''.
    0.55
     profits
    0.55
     emoji
    0.55
    bole
    0.55
    answered
    0.54
    Activations Density 2.021%

    No Known Activations