© 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. 0-RES-JB
    6. 7880
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "That" followed by a high degree of certainty or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "That" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     barg
    -0.57
     conv
    -0.57
     mort
    -0.55
     rank
    -0.55
     soon
    -0.55
     continuously
    -0.55
     lever
    -0.55
     community
    -0.54
     manual
    -0.53
     leisure
    -0.53
    POSITIVE LOGITS
     That
    2.72
    That
    2.05
     Those
    1.78
     Which
    1.59
     THAT
    1.56
     Then
    1.47
     Exactly
    1.43
     And
    1.42
     Because
    1.41
     They
    1.40
    Activations Density 0.036%

    No Known Activations