© 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. 3578
    Prev
    Next
    INDEX
    Explanations

    Twitter handles related to discussing films and movie concepts

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

    references to film industry discussions and censorship

    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
    etooth
    -0.80
     Ember
    -0.78
     peach
    -0.74
     FreeBSD
    -0.73
    Ò
    -0.72
     coils
    -0.71
     glucose
    -0.70
     Gly
    -0.70
     Hyd
    -0.69
     Runes
    -0.69
    POSITIVE LOGITS
     cinema
    2.29
     Cinema
    2.29
     Film
    2.20
     films
    2.19
     Films
    2.18
    Film
    2.17
     filmmakers
    2.17
     movie
    2.13
     film
    2.12
     filmmaking
    2.12
    Activations Density 0.863%

    No Known Activations