© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16407
    Prev
    Next
    INDEX
    Explanations

    questions starting with "why"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "why" indicating curiosity or questioning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pione
    -0.85
    vertisement
    -0.80
    aughed
    -0.78
    đ
    -0.78
    rawdownload
    -0.78
    û
    -0.78
    ù
    -0.78
    ÷
    -0.78
    ø
    -0.78
    Ă
    -0.77
    POSITIVE LOGITS
     they
    0.95
    soever
    0.88
     nobody
    0.88
     we
    0.85
     someone
    0.78
     somebody
    0.78
     people
    0.77
     anyone
    0.75
     THEY
    0.73
     exactly
    0.72
    Activations Density 0.060%

    No Known Activations