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. 19598
    Prev
    Next
    INDEX
    Explanations

    terms related to the Freedom of Information Act (FOIA) and related concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Freedom of Information Act

    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
     Jenner
    -0.66
     NHS
    -0.65
     Nickel
    -0.64
     Lutheran
    -0.64
     Turks
    -0.63
     regard
    -0.62
    lain
    -0.60
    naire
    -0.59
     defining
    -0.59
     PKK
    -0.58
    POSITIVE LOGITS
    LLOW
    1.28
    ogle
    1.10
    etus
    0.95
    FO
    0.94
    gey
    0.94
    ortun
    0.94
    overed
    0.93
    iled
    0.92
    avored
    0.90
    selage
    0.89
    Activations Density 0.009%

    No Known Activations