© 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. 22054
    Prev
    Next
    INDEX
    Explanations

    comparisons between different options or choices

    oai_token-act-pair · gpt-3.5-turbo

    comparisons between two items or concepts

    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
    olog
    -0.88
    ERN
    -0.80
    mberg
    -0.78
    shire
    -0.76
    overed
    -0.74
    lied
    -0.72
    unes
    -0.72
    Synopsis
    -0.70
    seed
    -0.70
    ocratic
    -0.69
    POSITIVE LOGITS
     mindset
    0.68
    hill
    0.66
    pecting
    0.63
     averages
    0.62
     scarcity
    0.62
     linear
    0.62
     bandits
    0.61
     nil
    0.60
     expend
    0.60
     underdog
    0.59
    Activations Density 0.016%

    No Known Activations