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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7688
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to talent, particularly in the context of sports and entertainment

    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
    1053
    +0.14
    0.5%
    1233
    +0.13
    0.5%
    1763
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1053
    +0.14
    0.02
    1512
    +0.13
    0.02
    1306
    +0.12
    0.02
    Negative Logits
     indestru
    -1.30
     apprehen
    -1.14
     intersper
    -1.13
     disagre
    -1.13
     emphat
    -1.08
     reluct
    -1.07
     intrigu
    -1.07
     impra
    -1.06
     depic
    -1.05
     inconce
    -1.02
    POSITIVE LOGITS
     talent
    1.42
     Talent
    1.22
     talents
    1.18
    Talent
    1.17
    talent
    1.12
     talento
    0.95
     talented
    0.93
     talentos
    0.79
     Talents
    0.77
     талан
    0.71
    Activations Density 0.074%

    No Known Activations