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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 18485
    Prev
    Next
    INDEX
    Explanations

    words related to negotiation or conflict resolution

    oai_token-act-pair · gpt-3.5-turbo

    uncommon or complex word forms, particularly those with repetitive or unique consonant patterns

    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
     Annotations
    -0.69
     Integrity
    -0.62
     Shuttle
    -0.61
     Scand
    -0.61
    Ĥª
    -0.60
     Awareness
    -0.58
     Prin
    -0.57
    Wan
    -0.57
     Fen
    -0.56
     Nem
    -0.55
    POSITIVE LOGITS
    ishly
    1.02
    efully
    0.92
    antly
    0.91
    kered
    0.89
    geoning
    0.87
    ingly
    0.82
    istically
    0.81
    icked
    0.80
    elled
    0.80
    aded
    0.79
    Activations Density 0.157%

    No Known Activations