© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6971
    Prev
    Next
    INDEX
    Explanations

    invitations or invitations-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "invitation" or "inviting" in various contexts

    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
     cleaner
    -0.74
    Ħ¢
    -0.73
     horizontally
    -0.69
     bare
    -0.69
     fab
    -0.66
    bian
    -0.63
    rous
    -0.62
     horizontal
    -0.62
    dress
    -0.61
    Reloaded
    -0.61
    POSITIVE LOGITS
    itations
    1.47
    itational
    1.39
    igor
    1.39
    incible
    1.34
    asion
    1.32
    itation
    1.30
    ocation
    1.29
    asions
    1.25
    ocations
    1.24
    oice
    1.24
    Activations Density 0.026%

    No Known Activations