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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 20565
    Prev
    Next
    INDEX
    Explanations

    **specific entities** like companies, organizations, games, academic papers, individuals, and other specified entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities, categories, or conditions associated with various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    perse
    -0.73
    heid
    -0.64
    Tro
    -0.60
    bah
    -0.60
    cknowled
    -0.59
    ĸļ
    -0.57
     condem
    -0.57
     Awakens
    -0.56
     Lia
    -0.56
     Sher
    -0.55
    POSITIVE LOGITS
    Ore
    0.70
     depending
    0.69
     (/
    0.68
     (<
    0.67
    ocations
    0.66
     imaginable
    0.65
     or
    0.65
     groups
    0.63
    Ì
    0.63
    ategories
    0.62
    Activations Density 0.279%

    No Known Activations