© 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. 967
    Prev
    Next
    INDEX
    Explanations

    words related to counting or ranking

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "first" and other ordinal indicators

    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
    redients
    -0.87
    rils
    -0.84
    ooks
    -0.82
    hend
    -0.78
    acent
    -0.77
    Keys
    -0.73
    stones
    -0.71
    grounds
    -0.70
    apons
    -0.70
    rs
    -0.70
    POSITIVE LOGITS
     time
    1.39
     occasion
    1.15
     instance
    1.13
     foray
    1.07
     occurrence
    1.07
     indication
    0.98
     times
    0.97
    time
    0.95
     sighting
    0.94
     installment
    0.92
    Activations Density 0.084%

    No Known Activations