© 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. 9-RES-JB
    11. 1994
    Prev
    Next
    INDEX
    Explanations

    specific criteria or guidelines outlined for various processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to criteria and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Champ
    -0.83
    sense
    -0.82
    anoia
    -0.80
    forts
    -0.78
    nces
    -0.77
    miah
    -0.76
    minus
    -0.75
    emonium
    -0.73
    rio
    -0.72
    lehem
    -0.72
    POSITIVE LOGITS
     determining
    1.54
     obtaining
    1.46
     accessing
    1.44
     selecting
    1.40
     evaluating
    1.35
     assigning
    1.34
     assessing
    1.33
     registering
    1.32
     handling
    1.32
     interpreting
    1.28
    Activations Density 0.329%

    No Known Activations