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. 7-RES-JB
    6. 8388
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals starting their own businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of businesses and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wake
    -0.72
    ãĥĥãĥī
    -0.70
    ãģĦ
    -0.70
    artz
    -0.68
     restraint
    -0.68
     precipitation
    -0.68
    ãĥ¤
    -0.67
     positives
    -0.64
     severity
    -0.62
     clarity
    -0.61
    POSITIVE LOGITS
     specializing
    1.11
    enium
    0.94
    eers
    0.83
    mates
    0.83
    girls
    0.81
     affiliated
    0.80
     headquartered
    0.77
    mate
    0.75
     LTD
    0.73
    ONY
    0.71
    Activations Density 0.360%

    No Known Activations