© 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. 14075
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with the letter "A"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or demographics, particularly starting with "A"

    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
    ":["
    -0.71
    iations
    -0.71
    Downloadha
    -0.69
    Contents
    -0.69
     encomp
    -0.65
    isSpecialOrderable
    -0.65
     thereof
    -0.63
     thereafter
    -0.63
     [|
    -0.62
     beforehand
    -0.62
    POSITIVE LOGITS
    UST
    0.97
     gunman
    0.97
     woman
    0.93
     protester
    0.89
     teenager
    0.87
    uckland
    0.83
    UG
    0.83
     man
    0.83
     spate
    0.81
     judge
    0.80
    Activations Density 0.140%

    No Known Activations