© 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. 20603
    Prev
    Next
    INDEX
    Explanations

    dates and years

    oai_token-act-pair · gpt-3.5-turbo

    numerical dates and time references

    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
    tsy
    -0.66
    drm
    -0.62
    Sov
    -0.60
    sonian
    -0.57
    ###
    -0.57
    Secondly
    -0.56
    nce
    -0.55
    tap
    -0.54
    son
    -0.53
    sw
    -0.52
    POSITIVE LOGITS
     respectively
    1.40
     inclusive
    1.29
     depending
    1.20
    depending
    1.16
     alike
    1.01
     periods
    0.76
     eras
    0.71
    SPONSORED
    0.71
     Streets
    0.67
     seasons
    0.66
    Activations Density 0.119%

    No Known Activations