© 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. 13424
    Prev
    Next
    INDEX
    Explanations

    the word "Cas" followed by a combination of letters

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Cas."

    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
    ¥ŀ
    -0.84
    doms
    -0.75
     nomine
    -0.75
     guiActiveUn
    -0.73
    é¾įå
    -0.73
    uyomi
    -0.71
     Malays
    -0.71
    ħĭ
    -0.71
    çīĪ
    -0.70
    ĪĴ
    -0.68
    POSITIVE LOGITS
     Cas
    1.18
    imir
    1.15
    arella
    0.95
    illo
    0.93
    atell
    0.92
    ques
    0.91
    Cas
    0.89
    abel
    0.88
    illi
    0.86
    iton
    0.86
    Activations Density 0.008%

    No Known Activations