© 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. 12974
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to oneself or other 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
    1187
    +0.10
    0.3%
    1861
    +0.10
    0.3%
    1256
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    990
    +0.10
    0.03
    1861
    +0.10
    0.04
    1187
    +0.10
    0.03
    Negative Logits
     emphat
    -0.70
     pessi
    -0.68
     marquer
    -0.66
     !...
    -0.65
     murano
    -0.63
     migli
    -0.62
    zupeł
    -0.62
     ciasc
    -0.62
     ?...
    -0.61
     NOO
    -0.61
    POSITIVE LOGITS
    selves
    1.06
    self
    0.96
    SELF
    0.95
     selves
    0.95
     Himself
    0.84
     yourself
    0.83
     herself
    0.83
     myself
    0.83
     themselves
    0.83
     ourselves
    0.83
    Activations Density 0.097%

    No Known Activations