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. 1332
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating ownership or possession

    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
    1961
    +0.14
    0.5%
    545
    +0.10
    0.3%
    1256
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.14
    0.02
    545
    +0.10
    0.02
    904
    +0.09
    0.01
    Negative Logits
     solidar
    -0.59
    Mó
    -0.55
    CÓ
    -0.53
     interessa
    -0.52
     talle
    -0.51
     sensibili
    -0.51
     cresce
    -0.50
    Referencoj
    -0.50
     sembler
    -0.49
    Cá
    -0.48
    POSITIVE LOGITS
     MINE
    0.95
     Ours
    0.94
     Yours
    0.94
     ours
    0.90
     Mine
    0.88
     mine
    0.86
     hers
    0.85
     theirs
    0.84
     yours
    0.82
    Mine
    0.81
    Activations Density 0.076%

    No Known Activations