© 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. 8566
    Prev
    Next
    INDEX
    Explanations

    numeric quantities or counts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that reference quantities or amounts

    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
    acus
    -0.73
    ahime
    -0.68
    omsday
    -0.67
    obook
    -0.67
     Pwr
    -0.67
     Includes
    -0.64
    icultural
    -0.64
    sein
    -0.63
     Currently
    -0.62
    oppable
    -0.62
    POSITIVE LOGITS
     nights
    1.30
     days
    1.17
     times
    1.15
     mornings
    1.10
     weeks
    1.08
     evenings
    1.07
     minutes
    1.05
     months
    1.03
     summers
    1.00
     acquaintances
    0.99
    Activations Density 0.243%

    No Known Activations