© 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. 4-RES-JB
    11. 15527
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the latter part of the year

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "late" associated with dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourge
    -0.81
    quished
    -0.78
    edIn
    -0.75
    apego
    -0.73
    IUM
    -0.71
    ointed
    -0.69
    recated
    -0.69
    utenberg
    -0.68
    inguished
    -0.68
    hyde
    -0.68
    POSITIVE LOGITS
     afternoon
    0.90
     infancy
    0.76
     innings
    0.73
     gestation
    0.72
     mornings
    0.71
     1970
    0.70
     increments
    0.70
    flight
    0.69
     fashion
    0.68
     manner
    0.68
    Activations Density 0.028%

    No Known Activations