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. 10920
    Prev
    Next
    INDEX
    Explanations

    references to industries or specific names of industries

    oai_token-act-pair · gpt-3.5-turbo

    references to various industries

    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
    astern
    -0.81
    plings
    -0.76
    borg
    -0.71
    tein
    -0.69
    ngth
    -0.69
    adder
    -0.68
     Ramsey
    -0.66
    engers
    -0.64
    olves
    -0.63
    blers
    -0.63
    POSITIVE LOGITS
    Indust
    0.96
    indust
    0.96
     Industry
    0.93
    Craft
    0.80
     Indust
    0.78
     sectors
    0.78
     Industries
    0.73
     sector
    0.73
     Enterprises
    0.73
     Sector
    0.71
    Activations Density 0.012%

    No Known Activations