© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3518
    Prev
    Next
    INDEX
    Explanations

    references to specific names or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    proper nouns and names, suggesting a focus on identifying individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    Þ
    -1.02
    ©¶æ
    -0.92
    ß
    -0.86
     exting
    -0.81
     bald
    -0.79
     withd
    -0.78
     exha
    -0.77
    ÃĥÃĤÃĥÃĤ
    -0.77
     ADS
    -0.77
    ortunately
    -0.76
    POSITIVE LOGITS
    aro
    1.44
    ino
    1.41
    ano
    1.40
    ito
    1.39
    io
    1.36
    imo
    1.32
    uno
    1.32
    ato
    1.30
    azo
    1.29
    eno
    1.29
    Activations Density 0.181%

    No Known Activations