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. 2826
    Prev
    Next
    INDEX
    Explanations

    descriptions of storytelling and narrative elements in text

    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
    +0.14
    0.5%
    1363
    +0.12
    0.5%
    1677
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.14
    0.02
    1435
    +0.12
    0.02
    1895
    +0.11
    0.02
    Negative Logits
     تضيفلها
    -0.52
    UpInside
    -0.50
    sho
    -0.49
    fficients
    -0.47
    Diweddarwch
    -0.46
     Health
    -0.46
    mpto
    -0.46
    Mucha
    -0.45
    dollis
    -0.45
    stylers
    -0.44
    POSITIVE LOGITS
     narrative
    1.19
     increa
    1.17
    Narrative
    1.15
     NARR
    1.11
     Narrative
    1.11
    narrative
    1.09
     narratives
    1.07
     scrat
    1.06
     impra
    1.04
     tolerably
    1.04
    Activations Density 0.084%

    No Known Activations