© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 7365
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referencing personal or communal attributes

    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
    1385
    +0.16
    0.5%
    1978
    +0.14
    0.4%
    478
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.16
    0.05
    144
    +0.14
    0.05
    1667
    +0.11
    0.05
    Negative Logits
     reconno
    -0.69
     apprehen
    -0.67
     gaily
    -0.66
     disreg
    -0.65
     ļ
    -0.64
     bénéfices
    -0.63
     interposed
    -0.63
     impra
    -0.60
     papild
    -0.60
     vainly
    -0.60
    POSITIVE LOGITS
     own
    1.00
     reputa
    0.75
     cristian
    0.72
    selves
    0.68
     inverte
    0.67
    Own
    0.67
     monaster
    0.66
     Own
    0.65
    own
    0.65
    sef
    0.65
    Activations Density 0.364%

    No Known Activations