© 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. 8-RES-JB
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    descriptions that denote a restricted quantity or availability

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the concept of "limited."

    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
    ilon
    -0.84
    ashington
    -0.78
    lyn
    -0.73
    idon
    -0.73
    ILLE
    -0.69
    attled
    -0.68
    ICAN
    -0.67
    tha
    -0.66
    CENT
    -0.66
    HEAD
    -0.65
    POSITIVE LOGITS
     minded
    0.89
     exceptions
    0.87
     liability
    0.84
     lifespan
    0.84
     amount
    0.83
    inous
    0.82
     quantities
    0.82
    sighted
    0.80
     edition
    0.79
     amounts
    0.79
    Activations Density 0.049%

    No Known Activations