© 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. 3562
    Prev
    Next
    INDEX
    Explanations

    phrases related to capabilities or objectives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to analytical evaluations and assessments

    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
    ctors
    -0.73
    ModLoader
    -0.73
     condem
    -0.64
    dule
    -0.64
     SD
    -0.61
    utters
    -0.57
    english
    -0.57
    usha
    -0.57
    idth
    -0.57
    prus
    -0.57
    POSITIVE LOGITS
     firsthand
    0.98
     ourselves
    0.91
     myself
    0.85
     yourself
    0.79
     vividly
    0.74
     empir
    0.73
     alone
    0.73
     yourselves
    0.73
    lessness
    0.70
     themselves
    0.69
    Activations Density 0.274%

    No Known Activations