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. 4-RES-JB
    6. 5244
    Prev
    Next
    INDEX
    Explanations

    words related to exhaust systems, particularly the term "exhaust" itself

    oai_token-act-pair · gpt-3.5-turbo

    terms related to exhaust systems and emissions

    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
     Pound
    -0.85
    llan
    -0.74
     Acqu
    -0.68
    HCR
    -0.66
     Lans
    -0.64
     Brav
    -0.61
    EEEE
    -0.61
     Americ
    -0.60
     Haram
    -0.59
     Mandela
    -0.59
    POSITIVE LOGITS
    ãĥ¼ãĥĨãĤ£
    1.05
    ively
    1.05
     fumes
    1.04
    haust
    0.99
    ptions
    0.94
     manifold
    0.92
     exhaust
    0.91
    ives
    0.90
    ivals
    0.85
     emission
    0.81
    Activations Density 0.013%

    No Known Activations