© 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. 1-RES-JB
    11. 18732
    Prev
    Next
    INDEX
    Explanations

    phrases related to The Beatles

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The Beatles" and related references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unal
    -0.80
     unde
    -0.72
    fecture
    -0.70
    trak
    -0.69
    resp
    -0.67
    nir
    -0.67
    inqu
    -0.66
    lege
    -0.66
    isites
    -0.65
    equ
    -0.64
    POSITIVE LOGITS
     Beatles
    1.08
    ipedia
    0.79
     Classics
    0.78
     Speedway
    0.75
    mania
    0.75
     Doodle
    0.74
     Circus
    0.74
     Orchestra
    0.72
     Fiesta
    0.69
     Revival
    0.68
    Activations Density 0.015%

    No Known Activations