© 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. 8329
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating durations or quantities

    oai_token-act-pair · gpt-3.5-turbo

    numbers that refer to quantities or durations related to events or experiences

    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
    abus
    -0.68
     backdrop
    -0.68
     tomorrow
    -0.64
    ifice
    -0.63
    react
    -0.63
    anka
    -0.61
     scapego
    -0.60
    wrapper
    -0.60
    adle
    -0.59
    =-=-=-=-=-=-=-=-
    -0.58
    POSITIVE LOGITS
     seasons
    1.51
     stint
    1.49
     years
    1.38
     decades
    1.18
    years
    1.15
     summers
    1.14
     winters
    1.12
     decade
    1.10
     months
    1.07
     career
    1.07
    Activations Density 0.110%

    No Known Activations