© 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. 6098
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial expenses or transactions

    oai_token-act-pair · gpt-3.5-turbo

    verb forms related to expansion

    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
    ball
    -0.80
    sonian
    -0.73
    creen
    -0.73
    mate
    -0.70
    FACE
    -0.69
    balls
    -0.69
    pas
    -0.68
    fully
    -0.68
    âĸ¬âĸ¬
    -0.67
    picking
    -0.66
    POSITIVE LOGITS
    onential
    1.54
    anded
    1.52
    ansion
    1.49
    osed
    1.36
    anding
    1.34
    onent
    1.26
    ression
    1.22
    ressed
    1.16
    ulsion
    1.15
    ressive
    1.04
    Activations Density 0.040%

    No Known Activations