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. 3-RES-JB
    6. 2459
    Prev
    Next
    INDEX
    Explanations

    names containing the pattern "erc" or similar sequences

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the name "Bercow" and related terms in a parliamentary context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Samoa
    -0.78
     Filip
    -0.78
     Alexa
    -0.70
     Cyrus
    -0.70
     Kinnikuman
    -0.69
     Sanford
    -0.67
     Narr
    -0.66
     Siberian
    -0.66
     Furious
    -0.66
     Avery
    -0.66
    POSITIVE LOGITS
    ourse
    1.20
    abulary
    1.13
    ourses
    1.10
    issions
    1.06
    zyk
    1.04
    amins
    0.99
    utonium
    0.99
    umbing
    0.98
     therap
    0.98
    onte
    0.97
    Activations Density 0.008%

    No Known Activations