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. 13324
    Prev
    Next
    INDEX
    Explanations

    specific groups of individuals like customers, fans, clients, donors, investors, parents, employers, critics

    oai_token-act-pair · gpt-3.5-turbo

    references to various stakeholders or audiences in relation to products or feedback

    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
     Presence
    -0.68
    owship
    -0.65
    iasis
    -0.64
    tein
    -0.61
     Thing
    -0.61
    UCK
    -0.60
    rection
    -0.58
    kun
    -0.55
     Bus
    -0.55
    osi
    -0.54
    POSITIVE LOGITS
    avers
    0.87
    hip
    0.78
    folk
    0.77
     wishing
    0.74
    untled
    0.74
    paces
    0.74
    alse
    0.73
     who
    0.72
    '
    0.71
    erv
    0.70
    Activations Density 0.258%

    No Known Activations