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. 8962
    Prev
    Next
    INDEX
    Explanations

    mentions of the proper noun "Rock."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Rock."

    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
    URES
    -0.73
     destro
    -0.72
     sidx
    -0.70
     tampering
    -0.70
     Chandra
    -0.68
     aver
    -0.68
    BILITIES
    -0.68
     confir
    -0.67
    urers
    -0.66
    terday
    -0.64
    POSITIVE LOGITS
    ledge
    1.06
    berry
    1.01
    castle
    0.99
    erness
    0.98
    ford
    0.97
    ingham
    0.94
    ete
    0.93
    Berry
    0.93
    Rock
    0.91
    cliffe
    0.90
    Activations Density 0.013%

    No Known Activations