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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23700
    Prev
    Next
    INDEX
    Explanations

    age-related information, such as specific ages and age descriptors

    oai_token-act-pair · gpt-3.5-turbo

    age indicators and related phrases

    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
     Versus
    -0.66
     Uni
    -0.64
     bye
    -0.62
     Tomorrow
    -0.62
     Anarchy
    -0.61
     subsidies
    -0.61
     peripher
    -0.61
     Proc
    -0.61
     Skies
    -0.59
     Replay
    -0.59
    POSITIVE LOGITS
    year
    1.36
    degree
    1.27
    minute
    1.22
    inch
    1.19
    eyed
    1.17
    pound
    1.15
    month
    1.10
    percent
    1.10
    hour
    1.10
    member
    1.09
    Activations Density 0.059%

    No Known Activations