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. 2-RES-JB
    6. 10074
    Prev
    Next
    INDEX
    Explanations

    terms related to investors or investments

    oai_token-act-pair · gpt-3.5-turbo

    references to investors and shareholders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avers
    -1.14
    mith
    -1.08
    hip
    -1.07
    heet
    -1.05
    hips
    -1.05
    paces
    -1.03
    chool
    -0.97
    poons
    -0.96
    ometimes
    -0.96
    cale
    -0.96
    POSITIVE LOGITS
    hood
    0.76
     witness
    0.69
    stown
    0.69
     pilot
    0.68
    ATH
    0.67
    lier
    0.66
    OUS
    0.64
    holder
    0.64
    \\\\\\\\\\\\\\\\
    0.63
     STA
    0.62
    Activations Density 0.036%

    No Known Activations