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. 15315
    Prev
    Next
    INDEX
    Explanations

    phrases related to surviving extreme conditions or remarkable stories of survival

    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
    198
    +0.20
    0.6%
    752
    +0.14
    0.4%
    872
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.20
    0.08
    752
    +0.14
    0.06
    16
    +0.11
    0.07
    Negative Logits
     decided
    -0.58
     -
    -0.56
     said
    -0.56
     re
    -0.55
    <eos>
    -0.54
     together
    -0.54
    ↵↵
    -0.53
    ↵
    -0.53
     must
    -0.53
     –
    -0.53
    POSITIVE LOGITS
     Traité
    1.34
     Février
    1.30
     Sén
    1.30
     Souha
    1.27
     Mémoires
    1.25
     Docteur
    1.24
     carrefour
    1.23
     curé
    1.23
     Áng
    1.22
     haer
    1.21
    Activations Density 0.715%

    No Known Activations