© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7152
    Prev
    Next
    INDEX
    Explanations

    specific film industry actions related to writing, directing, and producing projects

    oai_token-act-pair · gpt-3.5-turbo
    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
    ickr
    -0.74
    inventoryQuantity
    -0.70
    amd
    -0.70
    NOW
    -0.66
    rawdownloadcloneembedreportprint
    -0.64
    jri
    -0.64
    ctrl
    -0.64
    Register
    -0.63
    $$$$
    -0.62
    Cooldown
    -0.60
    POSITIVE LOGITS
     alongside
    0.86
     episodes
    0.85
     songs
    0.81
     Sins
    0.80
     portions
    0.80
     scenes
    0.77
     Shades
    0.76
     screenplay
    0.76
     Scenes
    0.74
     tunes
    0.73
    Activations Density 0.123%

    No Known Activations