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. 1398
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and public inquiries

    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
    75
    +0.10
    0.3%
    1174
    +0.10
    0.3%
    805
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.10
    0.06
    227
    +0.10
    0.06
    1820
    +0.09
    0.04
    Negative Logits
     anticipo
    -0.59
    heça
    -0.58
    Ethylbenzene
    -0.56
    asteroide
    -0.54
    Fordítás
    -0.53
     palio
    -0.51
     vena
    -0.51
    vapor
    -0.50
     imposs
    -0.50
     \%-
    -0.50
    POSITIVE LOGITS
     Irish
    0.96
     Ireland
    0.88
     irish
    0.86
    Irish
    0.85
     Dublin
    0.83
     Irishman
    0.82
     ireland
    0.81
    Dublin
    0.74
    irish
    0.74
     IRELAND
    0.74
    Activations Density 0.295%

    No Known Activations