© 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. 1-RES-JB
    11. 7384
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "jeep", especially within the context of transportation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "jeep"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.82
    raviolet
    -0.82
    ancial
    -0.74
    */(
    -0.69
    omaly
    -0.68
    姫
    -0.68
    ramid
    -0.67
    ipolar
    -0.65
     Dull
    -0.65
    Interstitial
    -0.65
    POSITIVE LOGITS
    hovah
    1.51
     je
    1.32
    ijn
    0.95
    opard
    0.83
    eps
    0.79
     Xie
    0.77
    ques
    0.76
    ez
    0.73
    ep
    0.73
    ij
    0.73
    Activations Density 0.003%

    No Known Activations