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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 2837
    Prev
    Next
    INDEX
    Explanations

    superlatives indicating the best option or choice

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert the superiority or excellence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idon
    -0.91
     Emer
    -0.71
    chy
    -0.68
    ping
    -0.67
    bara
    -0.65
    gypt
    -0.65
    aryn
    -0.65
     Pear
    -0.65
    kefeller
    -0.63
    iverpool
    -0.63
    POSITIVE LOGITS
    seller
    1.16
    sell
    0.96
     suited
    0.95
    iary
    0.88
    worst
    0.82
    hest
    0.79
    iaries
    0.77
    imates
    0.75
     odds
    0.72
    ower
    0.72
    Activations Density 0.039%

    No Known Activations