© 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. 24074
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Ike."

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "like" 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
     ILCS
    -0.89
    istics
    -0.77
    istry
    -0.73
    porary
    -0.66
    rooms
    -0.66
    amental
    -0.66
    stru
    -0.65
    istically
    -0.64
    ples
    -0.63
    ogyn
    -0.63
    POSITIVE LOGITS
    lihood
    0.93
    mens
    0.91
    bike
    0.86
    aukee
    0.76
    li
    0.73
    jriwal
    0.71
    wik
    0.71
    manship
    0.70
    IGH
    0.69
    anu
    0.67
    Activations Density 0.042%

    No Known Activations