© 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. 8-RES-JB
    11. 7042
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics

    oai_token-act-pair · gpt-3.5-turbo

    definite articles and quantifiers associated with numerical or financial data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tattoos
    -0.90
     buttons
    -0.81
     pedals
    -0.80
    bugs
    -0.77
     somet
    -0.73
     docs
    -0.73
     desires
    -0.71
     badges
    -0.70
     cards
    -0.70
     excuses
    -0.70
    POSITIVE LOGITS
     whopping
    1.41
     handful
    1.11
     slew
    1.06
     plethora
    1.01
     swath
    1.00
     dozen
    0.98
     fraction
    0.95
     sizeable
    0.95
    usterity
    0.94
     majority
    0.94
    Activations Density 0.522%

    No Known Activations