© 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. 11-RES-JB
    11. 1787
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity or measurement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention quantities or amounts

    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
    ħĭ
    -0.87
     Cosponsors
    -0.83
    most
    -0.80
    orst
    -0.78
    heid
    -0.78
    iors
    -0.77
    acus
    -0.71
    endants
    -0.70
    _(
    -0.70
    Ń·
    -0.67
    POSITIVE LOGITS
     money
    1.22
     time
    1.15
     effort
    1.03
     variance
    1.02
     material
    1.01
     paperwork
    1.01
     information
    1.00
     downtime
    0.98
     calories
    0.98
     manpower
    0.97
    Activations Density 0.126%

    No Known Activations