Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2656
    Prev
    Next
    INDEX
    Explanations

    instances of interaction and conflict between individuals in a professional setting

    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
    1150
    +0.19
    0.7%
    1224
    +0.12
    0.5%
    50
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.19
    0.02
    1013
    +0.12
    0.11
    1380
    +0.09
    0.00
    Negative Logits
     diable
    -0.60
     blos
    -0.58
     doman
    -0.58
     fure
    -0.57
     vnd
    -0.56
     !...
    -0.56
     chiff
    -0.55
     tupperware
    -0.55
     serai
    -0.54
     baf
    -0.54
    POSITIVE LOGITS
    Personensuche
    0.57
     resourceCulture
    0.56
    webElementXpaths
    0.55
    Билгалдахарш
    0.55
     Савезне
    0.52
    Manbalar
    0.51
    GEBURTSDATUM
    0.50
    oa̍t
    0.49
    DeleteBehavior
    0.49
     Instyt
    0.47
    Activations Density 2.618%

    No Known Activations