© 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. 1985
    Prev
    Next
    INDEX
    Explanations

    references to the word "Jeep"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the name "je" and the character "Raf."

    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
    ancial
    -0.80
    raviolet
    -0.78
    姫
    -0.77
    ãĥ´ãĤ¡
    -0.73
     Dull
    -0.72
    sworth
    -0.70
    ciating
    -0.68
    holders
    -0.66
    ntil
    -0.65
     weap
    -0.65
    POSITIVE LOGITS
    hovah
    1.52
     je
    0.97
    opard
    0.89
    eps
    0.87
    ques
    0.84
    pee
    0.84
    ep
    0.83
    neys
    0.82
    ijn
    0.82
    ff
    0.77
    Activations Density 0.006%

    No Known Activations