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. 15367
    Prev
    Next
    INDEX
    Explanations

    dates expressed in time and numbers with some emphasis on specific words

    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
    1056
    +0.09
    0.3%
    78
    +0.08
    0.2%
    50
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.09
    0.04
    1148
    +0.08
    0.03
    220
    +0.08
    0.04
    Negative Logits
     esternos
    -0.53
     poveznice
    -0.53
     bağlantılar
    -0.51
    : 
    -0.49
     Testamento
    -0.47
    Française
    -0.46
     Италијани
    -0.46
    RectangleBorder
    -0.45
     constate
    -0.44
    rativa
    -0.44
    POSITIVE LOGITS
     unwarran
    1.20
     unspeak
    1.15
     shewn
    1.09
     unlaw
    1.08
     onely
    1.05
     apprehen
    1.05
     Shakspeare
    1.05
     disreg
    1.05
     impractica
    1.04
     disagre
    1.03
    Activations Density 0.878%

    No Known Activations