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. 16075
    Prev
    Next
    INDEX
    Explanations

    solutions or actions suggested as responses to identified issues or problems

    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
    382
    +0.20
    0.6%
    2034
    +0.18
    0.6%
    1535
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.20
    0.10
    1535
    +0.18
    0.07
    610
    +0.16
    0.07
    Negative Logits
     reluct
    -1.47
     disagre
    -1.47
     maneu
    -1.47
     shenan
    -1.45
     disreg
    -1.43
     apprehen
    -1.40
     affor
    -1.39
     impra
    -1.37
     unwarran
    -1.35
     encomp
    -1.31
    POSITIVE LOGITS
     Also
    1.17
     Additionally
    1.11
     Furthermore
    1.02
    Also
    1.01
     Moreover
    0.98
    Additionally
    0.92
     Similarly
    0.88
    Furthermore
    0.86
    also
    0.86
     Other
    0.85
    Activations Density 0.427%

    No Known Activations