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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 4-RES-JB
    6. 5016
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly those related to "Gan" and "Kok"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly focusing on the name "Gan" and other related individuals

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

    No Comments

    Negative Logits
     seeker
    -0.77
    anwhile
    -0.74
    sburgh
    -0.70
     COURT
    -0.66
     BART
    -0.64
     Cassandra
    -0.63
     Patriot
    -0.62
     Parish
    -0.61
     magnitude
    -0.60
     referrals
    -0.60
    POSITIVE LOGITS
    omal
    1.05
    bare
    1.04
    esh
    1.04
    ryu
    0.99
    omen
    0.97
    zhou
    0.97
     Gan
    0.97
    zu
    0.92
    zeb
    0.92
    uin
    0.91
    Activations Density 0.011%

    No Known Activations