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. 15839
    Prev
    Next
    INDEX
    Explanations

    terms related to technological devices and operations

    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
    50
    +0.13
    0.4%
    1262
    +0.12
    0.4%
    406
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1137
    +0.13
    0.09
    1363
    +0.12
    0.08
    976
    +0.10
    0.08
    Negative Logits
    DockStyle
    -0.79
     correctes
    -0.78
     NKC
    -0.75
    पया
    -0.74
     Himo
    -0.71
     tenden
    -0.70
    CppMethod
    -0.70
     <<<<<<<<<<<<<<
    -0.70
     kosme
    -0.70
     Gesch
    -0.69
    POSITIVE LOGITS
     unspeak
    2.10
     apprehen
    1.85
     gaily
    1.80
     indescri
    1.71
     pamph
    1.63
     tolerably
    1.63
     vainly
    1.59
     reluct
    1.57
     disagre
    1.56
     shenan
    1.55
    Activations Density 1.029%

    No Known Activations