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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3677
    Prev
    Next
    INDEX
    Explanations

    references to box office performance

    oai_token-act-pair · gpt-3.5-turbo

    financial outcomes and box office performance of films

    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
    ocrates
    -0.82
    afety
    -0.80
    CHAT
    -0.78
    ierre
    -0.74
     [&
    -0.74
    Wiki
    -0.74
    ipedia
    -0.71
     administr
    -0.71
    practice
    -0.69
    cius
    -0.68
    POSITIVE LOGITS
     Furious
    1.14
     Paramount
    1.13
     Deadpool
    1.07
     Beasts
    1.05
     Jurassic
    1.04
     Pixar
    0.99
     nab
    0.96
     Ghostbusters
    0.96
     sequels
    0.95
     Lions
    0.95
    Activations Density 0.366%

    No Known Activations