© 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. 10-RES-JB
    11. 793
    Prev
    Next
    INDEX
    Explanations

    financial figures such as amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.77
     newsp
    -0.73
     behav
    -0.69
     compan
    -0.62
     culprit
    -0.61
    brainer
    -0.57
     behavi
    -0.57
     marqu
    -0.55
     antioxid
    -0.54
    hatt
    -0.53
    POSITIVE LOGITS
    000
    1.68
    050
    1.24
    030
    1.21
    900
    1.20
    660
    1.20
    060
    1.20
    820
    1.20
    712
    1.20
    040
    1.20
    045
    1.20
    Activations Density 0.078%

    No Known Activations