© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5084
    Prev
    Next
    INDEX
    Explanations

    references to economic figures and statistics

    oai_token-act-pair · gpt-3.5-turbo

    statements indicating monetary amounts or financial estimates

    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
    fml
    -0.63
    teness
    -0.60
    kward
    -0.58
    itars
    -0.57
    forts
    -0.57
     confidentiality
    -0.56
    erald
    -0.55
    gian
    -0.55
     Mechanical
    -0.55
    iosyncr
    -0.53
    POSITIVE LOGITS
     averaging
    1.18
     worth
    1.06
     costing
    1.01
     estimated
    0.93
     rated
    0.92
     valued
    0.87
     emitting
    0.86
     projected
    0.84
     twice
    0.84
     totaling
    0.82
    Activations Density 0.221%

    No Known Activations