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. 8226
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasts or comparisons

    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
    394
    +0.11
    0.3%
    1385
    +0.10
    0.3%
    16
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.11
    0.04
    3
    +0.10
    0.05
    16
    +0.08
    0.05
    Negative Logits
     apprehen
    -1.14
     reluct
    -1.12
     disagre
    -1.11
     disgra
    -1.11
     gaily
    -1.10
     reconno
    -1.02
     vainly
    -1.01
     tolerably
    -0.98
     inconce
    -0.97
     accla
    -0.97
    POSITIVE LOGITS
    теризу
    0.64
     EXPERIMENTS
    0.50
    rozco
    0.50
     abuelos
    0.50
    marginVertical
    0.50
    YOND
    0.49
    tifact
    0.49
     PLATES
    0.48
    Mə
    0.48
    Voltaje
    0.48
    Activations Density 0.310%

    No Known Activations