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. 7357
    Prev
    Next
    INDEX
    Explanations

    keywords related to invitations or requests

    oai_token-act-pair · gpt-3.5-turbo

    terms related to invitations and requests to participate

    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
    bard
    -0.74
    rupted
    -0.68
    rior
    -0.68
    ther
    -0.68
    icent
    -0.63
    arent
    -0.61
     Position
    -0.60
    astrous
    -0.59
     Rite
    -0.59
    scene
    -0.58
    POSITIVE LOGITS
     invitations
    1.13
     invitation
    1.02
     guests
    0.99
     invites
    0.79
    eers
    0.75
     invite
    0.75
     attendees
    0.74
    Inv
    0.73
     visitors
    0.73
     inviting
    0.72
    Activations Density 0.030%

    No Known Activations