© 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. 6-RES-JB
    11. 9585
    Prev
    Next
    INDEX
    Explanations

    keywords related to visual or performing arts, such as "screen," "stage," and "television."

    oai_token-act-pair · gpt-3.5-turbo

    references to media, particularly television and film

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    laus
    -0.71
    rils
    -0.71
    encer
    -0.68
     Torn
    -0.66
    ocate
    -0.66
    orically
    -0.65
    brace
    -0.65
    ernel
    -0.64
    rences
    -0.63
    unct
    -0.63
    POSITIVE LOGITS
     occasions
    1.09
     basis
    0.93
    ilts
    0.78
     behalf
    0.75
     pedest
    0.75
     whim
    0.72
     occasion
    0.71
     eve
    0.70
     shores
    0.68
     doorstep
    0.67
    Activations Density 0.164%

    No Known Activations