© 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. 9-RES-JB
    11. 11390
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation or critique

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that" used in various contexts related to opinions, critiques, or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ussia
    -0.85
    owder
    -0.85
    oby
    -0.72
    asures
    -0.70
    este
    -0.70
    thro
    -0.69
    ¶ħ
    -0.69
    rypt
    -0.68
    izont
    -0.67
    cycles
    -0.67
    POSITIVE LOGITS
    cher
    0.97
     begs
    0.91
     includes
    0.91
     sounds
    0.86
     leaves
    0.85
     doesn
    0.83
     culminated
    0.83
     pesky
    0.82
     hasn
    0.81
     translates
    0.81
    Activations Density 0.111%

    No Known Activations