© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5529
    Prev
    Next
    INDEX
    Explanations

    mentions of future events or advancements

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to upcoming events or future developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.92
    theless
    -0.85
    then
    -0.81
    lee
    -0.75
    umenthal
    -0.75
    xual
    -0.70
    ibu
    -0.69
    leeve
    -0.68
    iasis
    -0.68
    tics
    -0.67
    POSITIVE LOGITS
     generation
    1.23
     installment
    1.08
     step
    1.06
     logical
    0.97
     phase
    0.97
     chapter
    0.96
     iteration
    0.95
     incarnation
    0.93
     evolution
    0.90
     batch
    0.90
    Activations Density 0.044%

    No Known Activations