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. 6-RES-JB
    6. 22249
    Prev
    Next
    INDEX
    Explanations

    phrases related to catching a quick view or understanding of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "glimpse" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raid
    -0.88
    death
    -0.75
    bard
    -0.69
    iction
    -0.68
    die
    -0.67
    currency
    -0.67
     Balanced
    -0.66
    fighting
    -0.65
    erto
    -0.65
    ansom
    -0.64
    POSITIVE LOGITS
     glimps
    0.95
    seeing
    0.90
     glimpse
    0.81
    orial
    0.76
    ewitness
    0.76
     peek
    0.75
     afar
    0.74
     thereof
    0.71
    lights
    0.71
     hints
    0.70
    Activations Density 0.031%

    No Known Activations