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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13083
    Prev
    Next
    INDEX
    Explanations

    personal pronouns 'me' and 'myself' in sentences related to personal experiences and interactions

    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
    1187
    +0.15
    0.5%
    1413
    +0.12
    0.4%
    1839
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.15
    0.04
    1413
    +0.12
    0.04
    1055
    +0.12
    0.05
    Negative Logits
     aen
    -1.01
     kyo
    -0.97
     fua
    -0.97
     jaya
    -0.96
     wong
    -0.96
     emphat
    -0.96
     ?...
    -0.95
     tew
    -0.94
     kuro
    -0.94
     uhr
    -0.93
    POSITIVE LOGITS
     me
    1.01
     myself
    0.92
     Me
    0.88
    Me
    0.83
    me
    0.81
     ME
    0.79
    myself
    0.78
     my
    0.75
    my
    0.65
     Myself
    0.64
    Activations Density 0.129%

    No Known Activations