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. 2-RES-JB
    6. 16168
    Prev
    Next
    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially names and notable individuals

    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
    naire
    -0.83
    naires
    -0.83
    angible
    -0.79
    orer
    -0.77
    icket
    -0.73
    aston
    -0.72
    istics
    -0.71
    ingu
    -0.71
    tackle
    -0.70
    ifier
    -0.70
    POSITIVE LOGITS
    DEN
    0.99
     Nunes
    0.85
    TERN
    0.78
    irez
    0.78
    lus
    0.77
     Flore
    0.76
    66666666
    0.76
     Yates
    0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.74
    ı
    0.74
    Activations Density 0.022%

    No Known Activations