Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-RES-JB
    6. 20837
    Prev
    Next
    INDEX
    Explanations

    countries or names related to the name "Chad"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.86
    kefeller
    -0.68
    ãĤ¹ãĥĪ
    -0.68
    wow
    -0.67
    elsen
    -0.66
    ablishment
    -0.64
    naires
    -0.64
    kaya
    -0.64
    iday
    -0.63
    zzle
    -0.62
    POSITIVE LOGITS
    wick
    1.06
    riot
    0.92
    riots
    0.91
    lon
    0.81
    rina
    0.75
    rine
    0.73
    bage
    0.73
    ting
    0.72
    aldi
    0.71
    mi
    0.71
    Activations Density 0.072%

    No Known Activations