© 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. 0-RES-JB
    11. 2023
    Prev
    Next
    INDEX
    Explanations

    words related to collision or clash

    oai_token-act-pair · gpt-3.5-turbo

    words related to gliding techniques or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     electron
    -0.60
     OM
    -0.60
     questions
    -0.59
     hepat
    -0.58
     MG
    -0.58
     sequ
    -0.57
     strip
    -0.57
     Sev
    -0.56
     Lat
    -0.56
     engine
    -0.55
    POSITIVE LOGITS
    iding
    4.16
    ided
    2.69
    ides
    2.52
    iders
    2.25
    ider
    2.11
    ide
    2.10
    IDES
    1.81
    IDE
    1.79
    idal
    1.51
    IDER
    1.35
    Activations Density 0.008%

    No Known Activations