© 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. 22876
    Prev
    Next
    INDEX
    Explanations

    names or surnames of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns associated with individuals and places

    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
    lehem
    -0.56
    mble
    -0.54
    DIS
    -0.54
     division
    -0.54
    ymm
    -0.54
    akens
    -0.53
    erial
    -0.52
    mos
    -0.52
     grids
    -0.51
    ystem
    -0.51
    POSITIVE LOGITS
     himself
    1.05
    's
    1.01
     personally
    0.93
     Himself
    0.85
     Sr
    0.78
     Productions
    0.77
    igham
    0.76
     herself
    0.75
    iani
    0.74
     voicing
    0.68
    Activations Density 0.265%

    No Known Activations