© 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. 8-RES-JB
    11. 2396
    Prev
    Next
    INDEX
    Explanations

    words related to specific names

    oai_token-act-pair · gpt-3.5-turbo

    names or identifiers, particularly those related to people and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    backer
    -0.72
    kefeller
    -0.69
    govtrack
    -0.67
    ruary
    -0.65
    Xi
    -0.64
     <+
    -0.63
    isance
    -0.62
     pack
    -0.62
    ascript
    -0.62
    issance
    -0.60
    POSITIVE LOGITS
    oshi
    0.86
    azi
    0.82
    anga
    0.79
    chuk
    0.76
    ugu
    0.74
    iko
    0.73
    hya
    0.71
    abi
    0.70
    obiles
    0.70
    awk
    0.70
    Activations Density 0.155%

    No Known Activations