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. 15054
    Prev
    Next
    INDEX
    Explanations

    adjectives describing a high degree of something

    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
    478
    +0.23
    0.8%
    1870
    +0.13
    0.5%
    517
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.23
    0.03
    1776
    +0.13
    0.02
    517
    +0.12
    0.02
    Negative Logits
     présidenti
    -0.66
     abstrait
    -0.65
    hadur
    -0.56
     réaliste
    -0.55
    gyar
    -0.53
     privilégi
    -0.53
     typique
    -0.53
     magique
    -0.53
    fraz
    -0.52
     exécu
    -0.52
    POSITIVE LOGITS
    nemia
    0.83
    postolic
    0.82
     Ottobre
    0.81
     thermomix
    0.77
     Luglio
    0.75
     psycopg
    0.72
    highly
    0.71
    Highly
    0.71
     highly
    0.71
     democra
    0.70
    Activations Density 0.063%

    No Known Activations