© 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. 0-RES-JB
    11. 15266
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to conflation, confinement, or restriction

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conf" and its various contexts, often related to confinement or confusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    marked
    -0.82
    Blade
    -0.71
    eday
    -0.71
    tesy
    -0.70
    akedown
    -0.69
    ative
    -0.68
    rity
    -0.67
     Job
    -0.65
    average
    -0.65
     Zimmer
    -0.65
    POSITIVE LOGITS
     conf
    3.72
    conf
    1.60
     Conf
    1.56
    Conf
    1.52
     confounding
    1.21
     confuse
    1.03
     convol
    0.98
     supp
    0.97
     myst
    0.94
     confess
    0.93
    Activations Density 0.009%

    No Known Activations