© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6880
    Prev
    Next
    INDEX
    Explanations

    key features or updates within software or applications

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various software features

    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
    sis
    -0.77
    ça
    -0.77
    azar
    -0.73
    alg
    -0.72
    amn
    -0.71
    Ń·
    -0.70
    apy
    -0.69
    cel
    -0.69
    cffffcc
    -0.69
    oner
    -0.68
    POSITIVE LOGITS
     features
    0.97
    Features
    0.96
    Feature
    0.94
     Features
    0.92
    afety
    0.86
     enhancements
    0.79
    features
    0.78
     Include
    0.78
    feature
    0.77
    iveness
    0.77
    Activations Density 0.024%

    No Known Activations