© 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. 10340
    Prev
    Next
    INDEX
    Explanations

    references to the genre of rap music

    oai_token-act-pair · gpt-3.5-turbo

    references to rap music

    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
    ertodd
    -0.89
    fman
    -0.88
    ++++++++++++++++
    -0.76
    Split
    -0.74
     Samar
    -0.73
     Lumpur
    -0.72
     Shares
    -0.69
     Columb
    -0.68
     Lauder
    -0.68
    ########
    -0.66
    POSITIVE LOGITS
    acious
    1.05
    itone
    1.01
    acity
    1.00
     rap
    0.92
    iton
    0.86
    hett
    0.83
    isphere
    0.83
    heet
    0.81
    ican
    0.81
     sheet
    0.81
    Activations Density 0.009%

    No Known Activations