© 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. 1-RES-JB
    11. 1009
    Prev
    Next
    INDEX
    Explanations

    names of individuals, with a particular emphasis on the name "Julius"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Julius," "Johannes," and "Julio."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raising
    -0.86
    erer
    -0.84
    rage
    -0.84
    rain
    -0.82
    empl
    -0.80
    join
    -0.79
    ramid
    -0.77
    ple
    -0.77
    bare
    -0.77
    ship
    -0.76
    POSITIVE LOGITS
     Julius
    1.45
     Caesar
    0.97
    BuyableInstoreAndOnline
    0.89
    çIJ
    0.87
     Berger
    0.87
     Ny
    0.80
     Moz
    0.79
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.78
     Bryant
    0.77
    ensor
    0.77
    Activations Density 0.008%

    No Known Activations