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. 8554
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named "Brock"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Brock" in various contexts

    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
    gered
    -0.72
     conspicuous
    -0.69
    dfx
    -0.67
    ffic
    -0.67
     SERVICE
    -0.66
    ired
    -0.65
     cytok
    -0.63
     CoC
    -0.62
    udic
    -0.62
     socket
    -0.61
    POSITIVE LOGITS
     Brock
    1.04
    lings
    0.98
    mire
    0.92
    leys
    0.86
    halla
    0.86
     Upton
    0.86
    hurst
    0.84
    strap
    0.83
    stre
    0.83
    ham
    0.82
    Activations Density 0.008%

    No Known Activations