© 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. 5144
    Prev
    Next
    INDEX
    Explanations

    large dollar amounts or numbers expressed in digits

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary values or financial figures

    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
     viz
    -0.63
    laws
    -0.59
    rollers
    -0.58
     Rend
    -0.57
     Slav
    -0.57
    leading
    -0.55
    poke
    -0.55
    lines
    -0.53
     grounding
    -0.53
    reditary
    -0.52
    POSITIVE LOGITS
     million
    1.06
     billion
    1.05
    billion
    1.03
     trillion
    1.02
    million
    1.01
    bn
    0.93
    -$
    0.93
    125
    0.87
     Billion
    0.87
     apiece
    0.86
    Activations Density 0.050%

    No Known Activations