© 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. 8-RES-JB
    11. 9067
    Prev
    Next
    INDEX
    Explanations

    "<end>`" symbols of various contexts

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly variations of 'â' and 'ł'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reflex
    -0.71
     pleasure
    -0.65
     condem
    -0.64
     fuck
    -0.64
     Lama
    -0.64
     indo
    -0.63
     asshole
    -0.62
     hung
    -0.62
     Sammy
    -0.62
     donkey
    -0.62
    POSITIVE LOGITS
    ï¸ı
    0.99
    ternity
    0.85
    uthor
    0.85
     denotes
    0.78
    _>
    0.78
    STEM
    0.75
    pecially
    0.72
    ãĥ´ãĤ¡
    0.71
    there
    0.70
    ACP
    0.69
    Activations Density 0.245%

    No Known Activations