© 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. 7-RES-JB
    11. 1764
    Prev
    Next
    INDEX
    Explanations

    names or references related to "Cro" in a variety of contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Cro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.82
    imental
    -0.77
    manship
    -0.76
    LESS
    -0.76
    uated
    -0.70
    uating
    -0.70
    gency
    -0.68
    iating
    -0.66
    UAL
    -0.66
    ãĥ¼ãĥĨãĤ£
    -0.65
    POSITIVE LOGITS
    oked
    1.13
    chet
    1.08
    oks
    1.07
    pper
    1.06
    bones
    1.01
    ppo
    1.00
    ppers
    0.98
    osph
    0.98
    tch
    0.96
    opa
    0.94
    Activations Density 0.011%

    No Known Activations