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. 4-RES-JB
    6. 23153
    Prev
    Next
    INDEX
    Explanations

    names or references that include the term "di"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals named Mahdi

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

    No Comments

    Negative Logits
    manship
    -0.75
    ilater
    -0.71
    erous
    -0.68
    Reviewer
    -0.67
    INGS
    -0.65
     Eliot
    -0.64
    eers
    -0.62
     EVs
    -0.62
    ties
    -0.62
     Valkyrie
    -0.62
    POSITIVE LOGITS
    plom
    1.24
    abetes
    1.23
    ocese
    1.11
    ablo
    1.11
    urnal
    1.10
    ploma
    1.10
    agonal
    1.07
    agram
    1.07
    oche
    0.94
    agh
    0.91
    Activations Density 0.006%

    No Known Activations