© 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. 2-RES-JB
    11. 4257
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    the names of individuals or entities, particularly in connection to events or actions

    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
    ection
    -0.79
    iveness
    -0.76
    ected
    -0.76
    esthetic
    -0.76
    oaded
    -0.74
    pocket
    -0.72
    uctions
    -0.70
    ļéĨĴ
    -0.69
    plates
    -0.69
    tips
    -0.69
    POSITIVE LOGITS
    stal
    1.10
     Reign
    0.86
    acci
    0.76
     Cron
    0.74
    agher
    0.73
    aldi
    0.73
     Wyatt
    0.70
    kus
    0.69
    sum
    0.68
     Warlock
    0.66
    Activations Density 0.011%

    No Known Activations