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. 14006
    Prev
    Next
    INDEX
    Explanations

    references to crime incidents and legal actions

    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
    +0.14
    0.5%
    1535
    +0.13
    0.5%
    453
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.14
    0.09
    1896
    +0.13
    0.05
    1780
    +0.13
    0.05
    Negative Logits
     fto
    -1.20
     fta
    -1.17
     thut
    -1.14
     bénéficiaire
    -1.12
     Traité
    -1.12
     jaya
    -1.10
     chande
    -1.09
     medesimo
    -1.04
     ftu
    -1.04
     fep
    -1.04
    POSITIVE LOGITS
     few
    0.81
     lot
    0.81
     couple
    0.79
    Einen
    0.72
     handful
    0.69
     large
    0.67
     bit
    0.65
     bunch
    0.65
     significant
    0.64
     huge
    0.63
    Activations Density 0.448%

    No Known Activations