© 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. 9630
    Prev
    Next
    INDEX
    Explanations

    words related to television ratings

    oai_token-act-pair · gpt-3.5-turbo

    discussions related to television ratings

    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
     Alm
    -0.73
     Barr
    -0.70
     Ric
    -0.70
     Gibbs
    -0.68
     Roses
    -0.68
     Alz
    -0.68
    uve
    -0.68
    adr
    -0.68
     Poe
    -0.67
    lessness
    -0.67
    POSITIVE LOGITS
     ratings
    1.22
     rating
    0.91
    Reviewer
    0.82
     surge
    0.78
     Ratings
    0.78
     soar
    0.78
    awed
    0.77
    hare
    0.77
    undown
    0.71
     soared
    0.69
    Activations Density 0.022%

    No Known Activations