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. 3-RES-JB
    6. 1010
    Prev
    Next
    INDEX
    Explanations

    adjectives that imply superiority, excellence, or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating optimal solutions or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idon
    -0.79
    chy
    -0.68
     Emer
    -0.67
    aryn
    -0.65
     Pear
    -0.64
    kefeller
    -0.63
    iverpool
    -0.63
     probing
    -0.61
     Dru
    -0.61
    onut
    -0.61
    POSITIVE LOGITS
    seller
    1.10
     suited
    0.95
    iary
    0.93
    sell
    0.91
    iaries
    0.87
    ower
    0.80
    ow
    0.79
    imates
    0.79
    ector
    0.77
    friends
    0.76
    Activations Density 0.036%

    No Known Activations