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. 10-RES-JB
    6. 13627
    Prev
    Next
    INDEX
    Explanations

    information related to the age of individuals

    oai_token-act-pair · gpt-3.5-turbo

    information related to age and demographics of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akedown
    -0.73
    stasy
    -0.71
     neighb
    -0.69
    bernatorial
    -0.64
     metast
    -0.63
    vernment
    -0.63
    aucuses
    -0.60
     compan
    -0.60
     precincts
    -0.59
    gregation
    -0.59
    POSITIVE LOGITS
     winger
    0.83
    native
    0.81
     native
    0.78
     Frenchman
    0.77
     versatile
    0.75
     midfielder
    0.72
     striker
    0.70
    year
    0.68
    quart
    0.64
     veteran
    0.62
    Activations Density 0.087%

    No Known Activations