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. 15546
    Prev
    Next
    INDEX
    Explanations

    information about a person's background and life events

    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
    381
    +0.18
    0.6%
    50
    +0.17
    0.6%
    2019
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.18
    0.10
    862
    +0.17
    0.04
    1510
    +0.14
    0.06
    Negative Logits
     matel
    -1.32
     affez
    -1.19
     soigne
    -1.12
     cannes
    -1.12
     trouva
    -1.11
     bordeaux
    -1.11
     canel
    -1.09
     bourgeo
    -1.08
     sement
    -1.08
     écl
    -1.07
    POSITIVE LOGITS
    <_>
    0.89
    Glej
    0.84
    astéro
    0.77
    Quiénes
    0.75
    Solución
    0.74
    Πηγές
    0.72
     became
    0.70
    destroyAll
    0.69
     went
    0.69
    المصادر
    0.68
    Activations Density 0.341%

    No Known Activations