© 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. 5362
    Prev
    Next
    INDEX
    Explanations

    names or references related to a specific person or character named "Ab"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual named "Ab"

    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
     Titanic
    -0.65
     touches
    -0.65
    ä¹ĭ
    -0.64
     Markus
    -0.64
     prick
    -0.61
     merit
    -0.60
     Solitaire
    -0.59
    ancial
    -0.58
     Acceler
    -0.58
     Appendix
    -0.58
    POSITIVE LOGITS
    olition
    1.28
    duction
    1.27
    raham
    1.25
    dullah
    1.17
    acus
    1.15
    duct
    1.14
    normal
    1.12
    rupt
    1.11
    orig
    1.10
    du
    1.10
    Activations Density 0.012%

    No Known Activations