© 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. 4-RES-JB
    11. 14924
    Prev
    Next
    INDEX
    Explanations

    references to the term "cast"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of the word "cast."

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

    No Comments

    Negative Logits
     proble
    -0.75
    uese
    -0.71
    aternal
    -0.69
    xtap
    -0.69
     mort
    -0.69
    erva
    -0.67
    ansom
    -0.67
    undai
    -0.65
     undermin
    -0.64
     incre
    -0.64
    POSITIVE LOGITS
    casting
    0.85
    leton
    0.80
    casters
    0.80
    aways
    0.79
    CAST
    0.77
    dar
    0.75
    ropolitan
    0.74
    л
    0.74
     Reborn
    0.72
    rons
    0.71
    Activations Density 0.013%

    No Known Activations