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. 19914
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and company names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific company or organization, particularly "Ars" and "Asus"

    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
     Nationwide
    -0.81
    bered
    -0.79
     Kimmel
    -0.74
    employment
    -0.71
     <+
    -0.65
     McMahon
    -0.65
    fulness
    -0.65
    taker
    -0.64
     UNC
    -0.63
     miscarriage
    -0.62
    POSITIVE LOGITS
    è
    0.95
     Skydragon
    0.83
     Ars
    0.79
    aldo
    0.78
    ensor
    0.77
    inet
    0.77
    antis
    0.77
    andom
    0.75
    Techn
    0.75
    isoft
    0.75
    Activations Density 0.009%

    No Known Activations