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. 1-RES-JB
    6. 5849
    Prev
    Next
    INDEX
    Explanations

    phrases related to the unleashing of actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to unleaded fuel and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.87
    ĸļ
    -0.82
     Kinnikuman
    -0.78
     International
    -0.75
    */(
    -0.74
     Gamergate
    -0.69
    ividual
    -0.69
    orno
    -0.68
     Seller
    -0.67
     Convention
    -0.65
    POSITIVE LOGITS
     unle
    1.26
    ritten
    0.88
    arning
    0.84
     rele
    0.83
    ashing
    0.82
    \\\\
    0.80
    ading
    0.77
    arded
    0.77
    arding
    0.76
    cks
    0.73
    Activations Density 0.008%

    No Known Activations