© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 8864
    Prev
    Next
    INDEX
    Explanations

    age-related information, specifically identifying the age of individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of ages, particularly in years

    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
    ramid
    -0.69
     conventions
    -0.66
    NRS
    -0.61
     satisf
    -0.59
     modes
    -0.57
     includ
    -0.57
     lows
    -0.56
    aples
    -0.56
     peripher
    -0.56
    theless
    -0.56
    POSITIVE LOGITS
    th
    1.04
    teenth
    0.90
    yr
    0.89
    rd
    0.88
    something
    0.82
    acious
    0.81
    cm
    0.80
    nd
    0.77
    year
    0.77
    %-
    0.76
    Activations Density 0.085%

    No Known Activations