© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 18514
    Prev
    Next
    INDEX
    Explanations

    references to movies and screenwriting activities

    oai_token-act-pair · gpt-3.5-turbo

    names of people involved in film production

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ibaba
    -0.82
    auna
    -0.80
     mosqu
    -0.80
     patrols
    -0.77
    Register
    -0.73
     Awareness
    -0.72
     Regist
    -0.70
     Cookies
    -0.67
    Activity
    -0.67
     disag
    -0.67
    POSITIVE LOGITS
     screenplay
    1.48
     Whedon
    1.34
     Spielberg
    1.29
     directing
    1.23
     Kubrick
    1.20
     Studios
    1.20
     scripting
    1.19
     studio
    1.19
     script
    1.16
     scripts
    1.16
    Activations Density 0.557%

    No Known Activations