Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9-RES-JB
    6. 11544
    Prev
    Next
    INDEX
    Explanations

    events, conferences, and gatherings that people attend

    oai_token-act-pair · gpt-3.5-turbo

    references to events and gatherings, particularly those involving political or scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.76
     smugglers
    -0.73
     porous
    -0.71
     looph
    -0.68
    vae
    -0.68
    sheets
    -0.68
     aliases
    -0.68
     subdiv
    -0.67
    raints
    -0.66
     hybrids
    -0.65
    POSITIVE LOGITS
     conference
    1.48
     summit
    1.42
    Fest
    1.42
     Summit
    1.34
     Conference
    1.30
     ceremony
    1.23
     Festival
    1.23
     banquet
    1.19
     Expo
    1.17
    conference
    1.17
    Activations Density 0.465%

    No Known Activations