Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20715
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that question the existence of something or highlight uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icial
    -0.58
     Seym
    -0.57
    EA
    -0.57
    Bio
    -0.55
    ãĥ¥
    -0.54
     IPM
    -0.53
    ME
    -0.53
     Warfare
    -0.52
    mes
    -0.52
    ocker
    -0.52
    POSITIVE LOGITS
    abouts
    1.37
     exists
    1.08
     are
    1.07
    upon
    1.03
     was
    0.99
     is
    0.98
     aren
    0.97
     were
    0.96
     isn
    0.95
     wasn
    0.94
    Activations Density 0.095%

    No Known Activations