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. 2921
    Prev
    Next
    INDEX
    Explanations

    descriptions and characteristics of individuals in a news article

    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
    227
    +0.11
    0.3%
    856
    +0.10
    0.3%
    453
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    648
    +0.11
    0.04
    227
    +0.10
    0.05
    743
    +0.10
    0.03
    Negative Logits
     lele
    -1.54
     bordeaux
    -1.51
     soggior
    -1.49
     milano
    -1.48
     nutr
    -1.46
     ivi
    -1.44
     doman
    -1.44
     tanga
    -1.40
     mef
    -1.38
     canel
    -1.37
    POSITIVE LOGITS
     likewise
    0.98
     similarly
    0.95
     meanwhile
    0.88
     also
    0.88
     agrees
    0.85
     echoed
    0.81
     agree
    0.81
     agreed
    0.78
     тоже
    0.78
     disagreed
    0.75
    Activations Density 0.262%

    No Known Activations