© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14187
    Prev
    Next
    INDEX
    Explanations

    mentions of leadership positions or titles, with a particular emphasis on the term "chief."

    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
    241
    +0.13
    0.5%
    168
    +0.11
    0.4%
    938
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    241
    +0.13
    0.03
    168
    +0.11
    0.03
    1575
    +0.11
    0.03
    Negative Logits
     apprehen
    -0.53
     tolerably
    -0.52
     reluct
    -0.52
     walla
    -0.48
     gaily
    -0.48
     withal
    -0.48
     annihilated
    -0.47
     endeavouring
    -0.47
     vainly
    -0.46
     horrend
    -0.46
    POSITIVE LOGITS
     chief
    1.19
    Chief
    1.17
     Chief
    1.14
    chief
    1.09
     CHIEF
    1.05
     Chiefs
    0.94
     chiefs
    0.89
    chiefs
    0.82
     ideolog
    0.70
     affari
    0.63
    Activations Density 0.055%

    No Known Activations