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. 8-RES-JB
    6. 16602
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific names, like "Berry" and "Brooks"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Berry" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    arty
    -0.95
    ugu
    -0.77
    othy
    -0.76
    uncture
    -0.68
    ODUCT
    -0.68
    uality
    -0.67
    apers
    -0.67
    achusetts
    -0.67
    phis
    -0.67
    allery
    -0.66
    POSITIVE LOGITS
    keley
    0.95
    lee
    0.78
    gger
    0.77
    ches
    0.76
    tics
    0.75
    cies
    0.74
    âķIJâķIJ
    0.74
     Hath
    0.73
    combe
    0.72
    zon
    0.69
    Activations Density 0.093%

    No Known Activations