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. 0-RES-JB
    6. 21798
    Prev
    Next
    INDEX
    Explanations

    the word "blanche" with different spellings

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "blanche" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     offic
    -0.65
     im
    -0.63
     Fruit
    -0.61
     pub
    -0.60
    liness
    -0.60
     MSI
    -0.60
     SSL
    -0.59
     Drinking
    -0.59
     circumstances
    -0.58
     lo
    -0.58
    POSITIVE LOGITS
    anche
    5.09
    anches
    2.51
    anch
    1.40
    anca
    1.32
    ithe
    1.15
    oche
    1.14
    anc
    1.12
    issance
    1.11
    onde
    1.02
    irie
    0.99
    Activations Density 0.008%

    No Known Activations