© 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. 3-RES-JB
    11. 58
    Prev
    Next
    INDEX
    Explanations

    words related to distribution and contribution

    oai_token-act-pair · gpt-3.5-turbo

    words related to distribution and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hypers
    -0.69
     Leather
    -0.68
     resolution
    -0.66
     linen
    -0.65
     Niet
    -0.64
     Dresden
    -0.62
     maturity
    -0.62
     Benson
    -0.62
     latex
    -0.62
     Friedman
    -0.61
    POSITIVE LOGITS
    iosyncr
    1.31
    ributes
    1.00
    ribut
    0.98
    itionally
    0.94
    ipel
    0.88
    ribute
    0.88
    uese
    0.84
    igham
    0.83
    elaide
    0.82
    ership
    0.81
    Activations Density 0.017%

    No Known Activations