© 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. 7-RES-JB
    11. 19485
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "the" followed by an action verb

    oai_token-act-pair · gpt-3.5-turbo

    the repeated word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    craft
    -0.76
     suppose
    -0.76
    ucl
    -0.70
     Leilan
    -0.69
    rade
    -0.69
    gat
    -0.66
    Malley
    -0.65
    razil
    -0.64
    recy
    -0.63
    utm
    -0.63
    POSITIVE LOGITS
     same
    1.78
    ses
    1.32
     hardest
    1.29
    same
    1.27
     slightest
    1.24
     latter
    1.24
     brunt
    1.22
     entire
    1.20
     entirety
    1.19
     remainder
    1.17
    Activations Density 0.302%

    No Known Activations