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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 3109
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    the word "the" in various contexts throughout the text

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

    No Comments

    Negative Logits
    craft
    -0.82
    claw
    -0.74
    each
    -0.68
    fw
    -0.68
     besides
    -0.67
    leeve
    -0.67
    abuse
    -0.67
    adoes
    -0.67
    ago
    -0.65
    rade
    -0.64
    POSITIVE LOGITS
     easiest
    1.27
     simplest
    1.22
     same
    1.18
     strongest
    1.17
     greatest
    1.15
     biggest
    1.13
     heaviest
    1.12
     largest
    1.11
     smallest
    1.10
     hardest
    1.09
    Activations Density 0.303%

    No Known Activations