© 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. 12509
    Prev
    Next
    INDEX
    Explanations

    the name "Arthur" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Arthur."

    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
    href
    -0.75
    ongyang
    -0.74
    initialized
    -0.73
    Ĥ¬
    -0.70
    ple
    -0.69
    racted
    -0.69
    ramid
    -0.68
    ered
    -0.68
    resent
    -0.67
    arity
    -0.66
    POSITIVE LOGITS
     Ashe
    1.09
     Arthur
    0.96
     Pend
    0.94
     Weasley
    0.93
     Conan
    0.86
    itic
    0.85
     Clarke
    0.81
    andise
    0.73
     Guinness
    0.72
    ite
    0.72
    Activations Density 0.010%

    No Known Activations