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. 444
    Prev
    Next
    INDEX
    Explanations

    phrases indicating superlatives or exceptional qualities

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating relationships and hierarchy

    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
    tera
    -0.90
    iture
    -0.81
    matter
    -0.79
     unfocusedRange
    -0.76
    rification
    -0.75
    ueller
    -0.71
    Ô
    -0.71
    miah
    -0.70
    hyde
    -0.70
    arity
    -0.68
    POSITIVE LOGITS
     sorts
    0.90
     earners
    0.83
     highs
    0.82
     contenders
    0.76
     lows
    0.75
     equals
    0.74
     pursuits
    0.74
     faiths
    0.72
     sinners
    0.72
     ones
    0.71
    Activations Density 0.065%

    No Known Activations