© 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. 3937
    Prev
    Next
    INDEX
    Explanations

    words related to the question of decision-making or consideration of options

    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
    554
    +0.14
    0.5%
    971
    +0.14
    0.5%
    1265
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    971
    +0.14
    0.04
    554
    +0.14
    0.04
    1810
    +0.11
    0.03
    Negative Logits
    ^{}
    -0.50
    <?
    -0.50
     discuter
    -0.49
    ⓧ
    -0.47
     susc
    -0.46
     Seleccione
    -0.45
     exerci
    -0.44
     étu
    -0.44
     KIA
    -0.44
     Rodrig
    -0.43
    POSITIVE LOGITS
     whether
    0.99
    whether
    0.90
     WHETHER
    0.87
     Whether
    0.80
    Whether
    0.78
     osal
    0.57
     mahd
    0.56
     there
    0.55
     للاسماء
    0.51
    inalg
    0.51
    Activations Density 0.076%

    No Known Activations