© 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. 12-RES-JB
    11. 4345
    Prev
    Next
    INDEX
    Explanations

    mentions of movie distribution platforms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to video or film formats and platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     writ
    -0.69
     Jur
    -0.64
     perpetual
    -0.62
     somet
    -0.60
     wit
    -0.59
     shr
    -0.59
     ple
    -0.58
     census
    -0.58
     ages
    -0.57
     unrestricted
    -0.57
    POSITIVE LOGITS
    imeo
    1.36
    ogue
    1.26
    ocal
    1.25
    ibe
    1.25
    arsity
    1.25
    ampires
    1.24
    ulture
    1.24
    HS
    1.21
    oodoo
    1.21
    ivid
    1.18
    Activations Density 0.023%

    No Known Activations