© 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. 9-RES-JB
    11. 3779
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Chaplin"

    oai_token-act-pair · gpt-3.5-turbo
    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
    ports
    -0.76
    enced
    -0.71
    WARD
    -0.67
    GGGGGGGG
    -0.66
    nings
    -0.65
    ences
    -0.64
    ative
    -0.63
     Gors
    -0.62
    ITED
    -0.62
     Gleaming
    -0.62
    POSITIVE LOGITS
    plain
    1.09
    anooga
    1.04
    plin
    0.96
    bara
    0.90
    agne
    0.89
    ulhu
    0.83
    ocobo
    0.81
    akra
    0.80
    unin
    0.78
    bones
    0.78
    Activations Density 0.102%

    No Known Activations