© 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. 10-RES-JB
    11. 18619
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly highlighting the last name "Urban."

    oai_token-act-pair · gpt-3.5-turbo

    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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dermat
    -0.72
     Tenth
    -0.71
    ENTS
    -0.71
     seat
    -0.71
    rences
    -0.71
     ADS
    -0.71
     depress
    -0.70
     Daryl
    -0.70
     Synd
    -0.70
     bald
    -0.68
    POSITIVE LOGITS
    o
    1.63
    olo
    1.31
    oco
    1.30
    aro
    1.28
    uno
    1.28
    ino
    1.27
    emo
    1.27
    azo
    1.26
    oro
    1.26
    oi
    1.24
    Activations Density 0.255%

    No Known Activations