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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18232
    Prev
    Next
    INDEX
    Explanations

    phrases related to convention centers and events

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of convention centers and related events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.91
    ï¸ı
    -0.73
    onen
    -0.66
    Downloadha
    -0.66
    ppe
    -0.66
    chev
    -0.66
    Mot
    -0.65
    inen
    -0.65
    cale
    -0.65
    Reply
    -0.63
    POSITIVE LOGITS
    enment
    0.83
     Dak
    0.72
     Disaster
    0.67
     Talent
    0.67
    iliation
    0.67
     Uncommon
    0.64
     Gleaming
    0.64
    pire
    0.61
     Integrity
    0.61
    iquette
    0.60
    Activations Density 0.804%

    No Known Activations