Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13422
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and movement

    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
    1757
    +0.13
    0.4%
    32
    +0.12
    0.4%
    674
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1757
    +0.13
    0.04
    645
    +0.12
    0.04
    1041
    +0.12
    0.03
    Negative Logits
     dicono
    -0.55
     Zeits
    -0.54
     purtroppo
    -0.53
     vogliamo
    -0.51
     kani
    -0.49
    ibatkan
    -0.49
     voglio
    -0.48
    Ve
    -0.48
     kala
    -0.47
     liev
    -0.47
    POSITIVE LOGITS
     around
    1.09
     AROUND
    1.06
    around
    1.03
     Around
    0.95
    Around
    0.90
    AROUND
    0.85
     paillettes
    0.81
     paisley
    0.74
     broderie
    0.73
     triomphe
    0.72
    Activations Density 0.092%

    No Known Activations