© 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. 5524
    Prev
    Next
    INDEX
    Explanations

    references to tool kits or sets that are available for purchase or use

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of kits and their features

    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
    arching
    -0.89
    ews
    -0.74
    unct
    -0.73
    acebook
    -0.68
     Democr
    -0.67
     Observatory
    -0.66
     Deity
    -0.65
     Marketable
    -0.63
     temptation
    -0.63
    nesota
    -0.62
    POSITIVE LOGITS
    chens
    1.28
    kit
    1.03
    kat
    1.02
     kit
    1.00
     kits
    0.96
     Kit
    0.81
     Kats
    0.79
    Kat
    0.78
    etsu
    0.78
    ilts
    0.75
    Activations Density 0.007%

    No Known Activations