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. 7-RES-JB
    6. 984
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "the" as a key indicator in various contexts

    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
    ambo
    -0.75
    etc
    -0.70
    ħĭ
    -0.70
     assume
    -0.70
    ribe
    -0.69
     partake
    -0.68
    FILE
    -0.67
    imi
    -0.63
    OTA
    -0.63
    sam
    -0.63
    POSITIVE LOGITS
     easiest
    1.24
     simplest
    1.05
     opposite
    1.01
     strongest
    1.01
     same
    1.00
     safest
    0.97
     weakest
    0.97
     culmination
    0.97
     toughest
    0.97
     greatest
    0.96
    Activations Density 0.096%

    No Known Activations