© 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. 20693
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and characters

    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
    ModLoader
    -0.71
    âĶĢâĶĢ
    -0.59
    terday
    -0.54
     CPC
    -0.52
    ãĥŁ
    -0.52
    theless
    -0.52
    acebook
    -0.52
     Fancy
    -0.51
     Italians
    -0.51
    etheless
    -0.51
    POSITIVE LOGITS
    zinski
    0.82
    erman
    0.77
    ansky
    0.76
    gaard
    0.76
    linger
    0.74
    lett
    0.74
    antz
    0.73
    ley
    0.73
    inski
    0.71
    burn
    0.71
    Activations Density 0.276%

    No Known Activations