© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    phrases related to business acquisitions and financial transactions

    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
    50
    +0.25
    0.9%
    752
    +0.13
    0.5%
    612
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.25
    0.04
    16
    +0.13
    0.04
    752
    +0.13
    0.03
    Negative Logits
     hombros
    -0.74
    astéroïdes
    -0.72
    UVWXYZ
    -0.71
    Ngoài
    -0.70
     simplifié
    -0.70
    ;%%
    -0.68
    enderror
    -0.67
    日閲覧
    -0.67
    Và
    -0.67
    asanjo
    -0.67
    POSITIVE LOGITS
     encomp
    2.32
     depic
    2.30
     affor
    2.27
     increa
    2.22
     reluct
    2.22
     Juf
    2.18
     volunte
    2.16
     snoopy
    2.15
     wherea
    2.15
     inev
    2.14
    Activations Density 0.182%

    No Known Activations