© 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. 10-RES-JB
    11. 10003
    Prev
    Next
    INDEX
    Explanations

    phrases related to causation or conditions that lead to specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" indicating relationships or connections in the text

    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
    èĪ
    -0.80
    Acknowled
    -0.72
    pent
    -0.70
    adia
    -0.68
    NM
    -0.65
    姫
    -0.65
    hare
    -0.64
    Tex
    -0.64
    cream
    -0.64
    MEN
    -0.63
    POSITIVE LOGITS
    cher
    0.95
     pesky
    0.90
    ched
    0.86
    chers
    0.86
     fateful
    0.84
     is
    0.83
     includes
    0.81
     elusive
    0.78
     sort
    0.77
     same
    0.76
    Activations Density 0.124%

    No Known Activations