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

    Neuronpedia

    Jacobian LensNEW
    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. 14672
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to actions and behaviors

    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
    2019
    +0.15
    0.5%
    50
    +0.15
    0.5%
    1415
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.15
    0.07
    1919
    +0.15
    0.09
    1510
    +0.13
    0.06
    Negative Logits
     tremb
    -1.59
     Mlle
    -1.53
     Keny
    -1.43
     Juf
    -1.43
     bordeaux
    -1.41
     Abbé
    -1.41
     napoli
    -1.40
     ibiza
    -1.40
     cannes
    -1.38
     tranquillo
    -1.37
    POSITIVE LOGITS
     seek
    0.85
     strive
    0.84
     utilize
    0.84
     create
    0.84
     rely
    0.83
     provide
    0.82
     do
    0.81
     ensure
    0.78
     apply
    0.77
     give
    0.76
    Activations Density 0.507%

    No Known Activations