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. 13624
    Prev
    Next
    INDEX
    Explanations

    phrases related to executives and leadership roles

    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
    +0.17
    0.7%
    260
    +0.13
    0.5%
    1272
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.17
    0.03
    1272
    +0.13
    0.03
    1352
    +0.13
    0.03
    Negative Logits
     skimage
    -0.59
    opsida
    -0.52
    كيفية
    -0.49
    ഔ
    -0.48
    ngOnDestroy
    -0.46
     pylab
    -0.45
    aucun
    -0.44
    MouseAdapter
    -0.43
    ॥
    -0.42
    getYear
    -0.41
    POSITIVE LOGITS
     executive
    1.30
     Executive
    1.20
    executive
    1.17
    Executive
    1.13
     EXECUTIVE
    1.10
     executives
    1.04
     exec
    1.02
    EXECUTIVE
    1.02
     Executives
    0.92
     Exec
    0.90
    Activations Density 0.043%

    No Known Activations