© 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. 11-RES-JB
    11. 2407
    Prev
    Next
    INDEX
    Explanations

    locations or political appointments

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns, particularly names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Basil
    -1.02
     Baird
    -0.96
     Aero
    -0.93
     Mel
    -0.83
     Ther
    -0.81
     inev
    -0.77
     Ake
    -0.77
    Ther
    -0.76
    avorite
    -0.75
     Carolyn
    -0.75
    POSITIVE LOGITS
    ri
    1.19
    ong
    1.04
     Mong
    0.91
    RI
    0.88
    stein
    0.88
    rient
    0.87
    VI
    0.85
    liga
    0.84
    ouri
    0.83
    FORM
    0.81
    Activations Density 0.286%

    No Known Activations