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. 10-RES-JB
    6. 275
    Prev
    Next
    INDEX
    Explanations

    locations or events related to political or public gatherings

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to significant events and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porous
    -0.86
     corro
    -0.78
     unreliable
    -0.77
     liar
    -0.76
     hybrids
    -0.76
     constructs
    -0.75
     subdiv
    -0.74
     retard
    -0.73
     mutated
    -0.73
     defective
    -0.73
    POSITIVE LOGITS
    Fest
    1.56
    iversary
    1.37
     Celebration
    1.28
    fest
    1.26
    posium
    1.24
    ftime
    1.22
     Festival
    1.21
     festivities
    1.19
    conference
    1.14
    alloween
    1.11
    Activations Density 0.393%

    No Known Activations