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. 4738
    Prev
    Next
    INDEX
    Explanations

    terms related to granting approval or permission

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to permission or approval

    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
    sonian
    -1.01
    lycer
    -0.78
    enth
    -0.75
    ulz
    -0.75
    acus
    -0.74
     resil
    -0.71
     depth
    -0.69
    inth
    -0.69
    athering
    -0.68
    myra
    -0.67
    POSITIVE LOGITS
     waivers
    0.94
     approvals
    0.85
     nomination
    0.76
    eous
    0.75
     holders
    0.75
     revocation
    0.74
    oned
    0.74
    ances
    0.74
    label
    0.73
    osate
    0.73
    Activations Density 0.061%

    No Known Activations