© 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. 6875
    Prev
    Next
    INDEX
    Explanations

    specific instances of the word "the" that are associated with other words

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    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
     namely
    -0.68
    SPONSORED
    -0.63
     besides
    -0.61
     accordingly
    -0.59
     thereby
    -0.56
     beforehand
    -0.56
     without
    -0.55
    thood
    -0.55
     owing
    -0.55
     nevertheless
    -0.55
    POSITIVE LOGITS
     aforementioned
    0.92
     entirety
    0.91
     same
    0.89
     largest
    0.89
     smallest
    0.87
     slightest
    0.86
     entire
    0.85
     latest
    0.82
     latter
    0.82
    oret
    0.82
    Activations Density 1.240%

    No Known Activations