© 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. 9-RES-JB
    11. 13943
    Prev
    Next
    INDEX
    Explanations

    descriptions and evaluations of fictional worlds or settings

    oai_token-act-pair · gpt-3.5-turbo

    elements related to film critique and storytelling structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fax
    -0.80
     leased
    -0.73
    Federal
    -0.69
    heid
    -0.68
     Suppose
    -0.68
    Lago
    -0.65
    ļéĨĴ
    -0.65
    exempt
    -0.65
     federally
    -0.64
     Today
    -0.64
    POSITIVE LOGITS
    Characters
    1.16
     realism
    1.09
     themes
    1.08
     cinematic
    1.07
     belie
    1.05
     believable
    1.04
     characters
    1.04
     pacing
    1.04
     storytelling
    1.03
     gore
    1.01
    Activations Density 1.112%

    No Known Activations