© 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. 15664
    Prev
    Next
    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names associated with individuals or entities

    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
    rophe
    -0.59
     duration
    -0.58
     Cooldown
    -0.57
    erver
    -0.57
     holiest
    -0.55
    width
    -0.55
     mileage
    -0.55
     blat
    -0.54
    SOURCE
    -0.53
     lid
    -0.53
    POSITIVE LOGITS
    neys
    0.96
    ernaut
    0.83
    ilee
    0.81
    usalem
    0.79
    etus
    0.77
    okia
    0.76
    isco
    0.75
    iard
    0.75
    iffe
    0.74
    eki
    0.73
    Activations Density 0.086%

    No Known Activations