© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6917
    Prev
    Next
    INDEX
    Explanations

    the word "relevant" and its variations

    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
    331
    +0.12
    0.4%
    812
    +0.12
    0.4%
    1265
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.12
    0.02
    1451
    +0.12
    0.02
    869
    +0.12
    0.02
    Negative Logits
     vœ
    -0.64
     demandent
    -0.64
    Törté
    -0.63
     dévou
    -0.59
     mettent
    -0.59
     placée
    -0.58
    Mű
    -0.58
     soutenu
    -0.58
     décrire
    -0.58
     Matériau
    -0.57
    POSITIVE LOGITS
     relevant
    0.96
     relevance
    0.92
    relevant
    0.86
     Relevant
    0.85
     relevan
    0.77
    Relevant
    0.75
    relevance
    0.75
     Relevance
    0.74
     irrelevant
    0.74
     relevante
    0.70
    Activations Density 0.080%

    No Known Activations