© 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. 3549
    Prev
    Next
    INDEX
    Explanations

    personal pronouns ('we' and 'I') mixed with verbs indicating actions

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

    the pronoun "we" indicating collective actions or sentiments

    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
    Redd
    -0.62
     Centauri
    -0.57
    CLASSIFIED
    -0.56
    WithNo
    -0.55
    WARD
    -0.54
    à
    -0.54
    âĢ¢âĢ¢
    -0.54
     Flavoring
    -0.54
    ¿½
    -0.53
     millenn
    -0.53
    POSITIVE LOGITS
    bsite
    1.03
    're
    1.02
    've
    1.01
    athered
    0.97
     recommend
    0.95
    ighed
    0.94
    asel
    0.92
    arers
    0.91
     strive
    0.90
    ird
    0.88
    Activations Density 0.167%

    No Known Activations