© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 3560
    Prev
    Next
    INDEX
    Explanations

    strings that relate to computer programming concepts and actions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to data processing and connectivity in technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conced
    -0.62
    illard
    -0.61
    Ü
    -0.56
     Santana
    -0.55
    æĪ¦
    -0.55
    iane
    -0.55
    stood
    -0.54
    é¾įå
    -0.54
     demoral
    -0.53
    icult
    -0.52
    POSITIVE LOGITS
     onto
    1.38
     into
    1.12
     directly
    1.04
     INTO
    1.03
     manually
    1.00
    into
    1.00
     thereto
    0.99
     to
    0.98
    To
    0.97
    to
    0.95
    Activations Density 0.252%

    No Known Activations