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. 165
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer systems and programming

    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
    1473
    +0.14
    0.4%
    581
    +0.09
    0.3%
    227
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.14
    0.03
    581
    +0.09
    0.04
    990
    +0.09
    0.03
    Negative Logits
     hek
    -0.66
    queryInterface
    -0.66
     bont
    -0.65
     basili
    -0.59
     protes
    -0.58
     gero
    -0.56
     plak
    -0.56
     malin
    -0.53
    Portale
    -0.53
     makro
    -0.53
    POSITIVE LOGITS
     include
    1.04
     includes
    1.00
     Include
    0.82
     apprehen
    0.78
     tolerably
    0.77
     INCLUDE
    0.77
     Includes
    0.77
     disagre
    0.76
     comprises
    0.70
     consists
    0.70
    Activations Density 0.322%

    No Known Activations