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. 15066
    Prev
    Next
    INDEX
    Explanations

    locations or points in a narrative where actions or key events occur

    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
    474
    +0.09
    0.3%
    1108
    +0.08
    0.2%
    314
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    474
    +0.09
    0.03
    879
    +0.08
    0.02
    1502
    +0.07
    0.03
    Negative Logits
     ceea
    -0.42
     Nevertheless
    -0.42
     Cannot
    -0.41
    </h4>
    -0.41
     cannot
    -0.41
    ága
    -0.41
     ছ
    -0.40
     by
    -0.40
     ні
    -0.40
     Didn
    -0.40
    POSITIVE LOGITS
     dises
    0.88
     tanga
    0.85
     endom
    0.80
     dora
    0.79
     Minang
    0.79
     anton
    0.78
     abnorm
    0.76
     mef
    0.76
     huma
    0.75
     meis
    0.74
    Activations Density 0.183%

    No Known Activations