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. 6-RES-JB
    6. 8138
    Prev
    Next
    INDEX
    Explanations

    terms related to contracts, permissions, and agreements

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual, likely related to a corporation or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rons
    -0.69
     owl
    -0.67
    iquid
    -0.64
     Registrar
    -0.64
    iants
    -0.63
     pickups
    -0.62
    owler
    -0.60
    uracy
    -0.60
    ategory
    -0.60
     hawk
    -0.60
    POSITIVE LOGITS
    eker
    1.17
    gger
    1.09
    lda
    0.97
    brate
    0.96
    ller
    0.94
    llers
    0.89
    xy
    0.86
    vere
    0.86
    brates
    0.86
    vent
    0.84
    Activations Density 0.025%

    No Known Activations