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. 8-RES-JB
    6. 23202
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe frequency or prevalence

    oai_token-act-pair · gpt-3.5-turbo

    words related to time and frequency

    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
    eday
    -0.86
    ĺħ
    -0.84
     Tags
    -0.84
    OGR
    -0.69
    ydia
    -0.69
    ODY
    -0.65
    culosis
    -0.64
     Quote
    -0.64
    udo
    -0.64
    udos
    -0.64
    POSITIVE LOGITS
     illustrious
    0.90
     expansive
    0.88
     unstoppable
    0.85
     embattled
    0.84
     volatile
    0.84
     contradictory
    0.84
     conflicting
    0.83
     formidable
    0.82
     pristine
    0.82
     infinite
    0.81
    Activations Density 0.165%

    No Known Activations