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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14975
    Prev
    Next
    INDEX
    Explanations

    mentions of football defensive plays and statistics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.13
    0.4%
    1137
    +0.12
    0.4%
    144
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    576
    +0.13
    0.04
    1137
    +0.12
    0.03
    144
    +0.11
    0.03
    Negative Logits
     effe
    -1.23
     encomp
    -1.23
     nutr
    -1.22
     inev
    -1.22
     fuf
    -1.21
     suscep
    -1.20
     viciss
    -1.19
     claudia
    -1.18
     squa
    -1.18
     erad
    -1.17
    POSITIVE LOGITS
     defense
    1.15
    defense
    0.98
     defence
    0.97
     Defense
    0.93
     defenses
    0.91
     defensive
    0.90
    Defense
    0.89
     defensively
    0.86
     defend
    0.79
    defence
    0.79
    Activations Density 0.069%

    No Known Activations