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. 6-RES-JB
    6. 21357
    Prev
    Next
    INDEX
    Explanations

    words related to inspections or the act of inspecting

    oai_token-act-pair · gpt-3.5-turbo

    references to inspections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.79
    uscript
    -0.78
    erry
    -0.70
    idal
    -0.68
    ctory
    -0.68
    ---------
    -0.68
    peak
    -0.66
    cing
    -0.66
    isSpecialOrderable
    -0.66
    pop
    -0.65
    POSITIVE LOGITS
     inspection
    1.14
     inspections
    1.05
     inspected
    0.88
     Inspection
    0.86
     inspecting
    0.85
     inspect
    0.83
     technician
    0.81
     inspector
    0.81
     inspectors
    0.80
     screenings
    0.79
    Activations Density 0.024%

    No Known Activations