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. 8-RES-JB
    6. 21581
    Prev
    Next
    INDEX
    Explanations

    professions or roles related to specific industries

    oai_token-act-pair · gpt-3.5-turbo

    references to various professional roles and occupations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tropical
    -0.66
    bush
    -0.66
    croft
    -0.66
    osure
    -0.65
     Territories
    -0.62
    peat
    -0.62
     Virus
    -0.61
    lights
    -0.60
    mone
    -0.58
    ?????-
    -0.58
    POSITIVE LOGITS
    hip
    1.39
    hips
    1.19
    paces
    1.14
    mith
    0.97
     who
    0.95
    '
    0.90
     Guild
    0.90
     unions
    0.88
    ervatives
    0.88
     everywhere
    0.88
    Activations Density 0.362%

    No Known Activations