© 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. 10-RES-JB
    11. 3240
    Prev
    Next
    INDEX
    Explanations

    terms related to operations and procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to organizational or operational activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hus
    -0.80
    sonian
    -0.77
    apple
    -0.71
    vana
    -0.68
    artz
    -0.68
    arton
    -0.67
    Ĥª
    -0.67
    yu
    -0.66
    ipedia
    -0.65
    ipeg
    -0.64
    POSITIVE LOGITS
    ally
    1.03
    eering
    0.92
     tempo
    0.92
    ality
    0.85
     manuals
    0.81
     manual
    0.80
    ional
    0.75
     Manual
    0.74
     conducted
    0.73
    ament
    0.73
    Activations Density 0.045%

    No Known Activations