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. 15776
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to specific individuals

    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
    1741
    +0.19
    0.6%
    776
    +0.16
    0.5%
    381
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.19
    0.05
    397
    +0.16
    0.04
    1937
    +0.14
    0.06
    Negative Logits
     accla
    -0.90
     excru
    -0.90
     madonna
    -0.89
     suspic
    -0.87
     milf
    -0.87
     noël
    -0.86
     Messieurs
    -0.84
     diable
    -0.84
     inconce
    -0.83
     hentai
    -0.83
    POSITIVE LOGITS
    OGND
    0.71
     His
    0.67
    astéro
    0.65
    His
    0.65
     presence
    0.64
     ability
    0.61
     biggest
    0.60
    Его
    0.58
     goal
    0.58
    Sein
    0.57
    Activations Density 0.180%

    No Known Activations