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. 15098
    Prev
    Next
    INDEX
    Explanations

    software and technology-related terms and updates

    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
    1978
    +0.12
    0.4%
    453
    +0.11
    0.3%
    50
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.12
    0.04
    283
    +0.11
    0.01
    1257
    +0.10
    0.03
    Negative Logits
     intersper
    -1.64
     encomp
    -1.63
     shenan
    -1.57
     snoopy
    -1.53
     impra
    -1.50
     depic
    -1.49
     disagre
    -1.49
     increa
    -1.48
     apprehen
    -1.47
     unve
    -1.46
    POSITIVE LOGITS
     utop
    1.22
     balon
    1.13
     meras
    1.09
     ortop
    1.02
     marte
    1.02
     kosme
    1.00
     spion
    1.00
     tenda
    0.99
     teras
    0.99
     elek
    0.97
    Activations Density 0.159%

    No Known Activations