© 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. 11535
    Prev
    Next
    INDEX
    Explanations

    technical paths or commands

    oai_token-act-pair · gpt-3.5-turbo

    instances of the forward slash character

    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
     Moody
    -0.74
     African
    -0.67
     tender
    -0.67
     killer
    -0.64
     Faw
    -0.62
     Pepsi
    -0.61
     delic
    -0.61
     wagon
    -0.61
     relentlessly
    -0.61
     barg
    -0.60
    POSITIVE LOGITS
    \/\/
    1.42
    usr
    1.37
    Users
    1.26
    ËĪ
    1.23
    wcsstore
    1.20
    Film
    1.17
    ********************************
    1.15
    uploads
    1.12
    etc
    1.11
    proc
    1.11
    Activations Density 0.034%

    No Known Activations