Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 7009
    Prev
    Next
    INDEX
    Explanations

    sentences expressing strong emotions and reflections on teamwork and improvement

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

    collective and motivational language in sports contexts

    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
     millenn
    -0.96
     è£ıè
    -0.92
    CLASSIFIED
    -0.85
     behavi
    -0.85
    ãĤ´ãĥ³
    -0.85
    ¿½
    -0.85
    DonaldTrump
    -0.84
     practition
    -0.83
     citiz
    -0.82
     Palestin
    -0.78
    POSITIVE LOGITS
     played
    1.22
     coached
    1.16
     battled
    1.14
     competed
    1.13
     coach
    1.12
     scored
    1.05
     play
    1.05
     scrim
    0.99
     practiced
    0.95
     struggled
    0.93
    Activations Density 0.321%

    No Known Activations