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. 8401
    Prev
    Next
    INDEX
    Explanations

    details or statistics about products, events, or campaigns

    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
    1343
    +0.25
    1.0%
    1150
    +0.20
    0.8%
    1224
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.25
    0.04
    184
    +0.20
    0.01
    678
    +0.17
    0.03
    Negative Logits
    تقاوى
    -0.53
     незавершена
    -0.53
     biografias
    -0.51
    nonzero
    -0.49
    Життєпис
    -0.49
     noyau
    -0.48
    verbosity
    -0.47
    espé
    -0.45
     Decreto
    -0.43
     tartalomajánló
    -0.43
    POSITIVE LOGITS
     OPPORT
    0.63
     zima
    0.59
     lapto
    0.58
     puto
    0.52
     strategia
    0.51
     ASPECTS
    0.51
     chod
    0.51
     alha
    0.51
     toal
    0.50
     PHILOS
    0.50
    Activations Density 0.327%

    No Known Activations