© 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. 12228
    Prev
    Next
    INDEX
    Explanations

    numerical data related to numerical rankings or quantities within a given context

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable statistics or numerical information related to entities or institutions

    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
    icz
    -0.81
    tainment
    -0.72
    timer
    -0.71
    lance
    -0.70
    activation
    -0.69
    matter
    -0.67
    Quantity
    -0.67
    gery
    -0.66
    VERSION
    -0.66
    arity
    -0.65
    POSITIVE LOGITS
     finalists
    1.26
     applicants
    0.90
     nominees
    0.88
    teenth
    0.87
     remaining
    0.87
     candidates
    0.87
     contenders
    0.86
     categories
    0.83
     possible
    0.83
     surveyed
    0.82
    Activations Density 0.101%

    No Known Activations