© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12258
    Prev
    Next
    INDEX
    Explanations

    references to specific names and titles in a work-related context

    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
    +0.09
    0.3%
    80
    +0.09
    0.3%
    468
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1987
    +0.09
    0.05
    227
    +0.09
    0.08
    1166
    +0.09
    0.07
    Negative Logits
    Atsauces
    -0.77
     affez
    -0.73
     parteci
    -0.71
     raccomand
    -0.70
     cammin
    -0.70
     trover
    -0.69
     doveva
    -0.69
     scopri
    -0.69
     panik
    -0.68
     kosme
    -0.68
    POSITIVE LOGITS
    '
    0.72
    ’
    0.71
     indescri
    0.64
     insensible
    0.54
     bologna
    0.52
     beaute
    0.51
     indestru
    0.51
     ndarray
    0.50
     rascal
    0.50
    iosync
    0.49
    Activations Density 0.638%

    No Known Activations