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. 8268
    Prev
    Next
    INDEX
    Explanations

    phrases related to narrow concepts or limited perspectives

    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
    1376
    +0.15
    0.5%
    897
    +0.12
    0.4%
    1416
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1376
    +0.15
    0.02
    1218
    +0.12
    0.02
    240
    +0.12
    0.02
    Negative Logits
    citenamefont
    -0.50
    HttpPut
    -0.50
    adaptiveStyles
    -0.49
     ExecuteAsync
    -0.49
    -------
    
    -0.46
    aleg
    -0.46
     buk
    -0.45
     TextFormField
    -0.44
    WindowConstants
    -0.44
    Viitteet
    -0.43
    POSITIVE LOGITS
    Narrow
    1.30
     Narrow
    1.28
     narrow
    1.24
    narrow
    1.16
     narrowing
    1.09
     narrows
    1.08
     narrowed
    1.07
     narrower
    0.95
     narrowly
    0.90
    Lmfao
    0.73
    Activations Density 0.067%

    No Known Activations