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. 9-RES-JB
    6. 11798
    Prev
    Next
    INDEX
    Explanations

    ages stated as a number followed by "years old"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the age at which significant life events occur

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vernment
    -0.71
    pard
    -0.67
    alle
    -0.67
    alties
    -0.66
    eries
    -0.63
    endas
    -0.62
    aples
    -0.60
    DCS
    -0.60
    arel
    -0.58
    assets
    -0.58
    POSITIVE LOGITS
    ¿
    0.79
    ·
    0.79
     18
    0.76
    Age
    0.72
     age
    0.72
     nineteen
    0.71
    FontSize
    0.70
     ripe
    0.70
     eighteen
    0.69
    §
    0.68
    Activations Density 0.019%

    No Known Activations