© 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. 4244
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy changes or adjustments

    oai_token-act-pair · gpt-3.5-turbo
    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
    wine
    -0.66
    ا
    -0.65
    waters
    -0.65
     stereotype
    -0.65
     Sic
    -0.60
     Heller
    -0.57
    dies
    -0.57
     Nass
    -0.56
     Sung
    -0.56
     hung
    -0.56
    POSITIVE LOGITS
     effected
    1.15
     drastic
    1.07
     gradual
    0.93
     incremental
    0.89
     occur
    0.89
     undone
    0.89
     wrought
    0.84
     undo
    0.83
     occurring
    0.81
    foreseen
    0.80
    Activations Density 0.429%

    No Known Activations