© 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. 5818
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "tank"

    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
    228
    +0.17
    0.7%
    1527
    +0.14
    0.6%
    1376
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    228
    +0.17
    0.02
    1527
    +0.14
    0.02
    1515
    +0.13
    0.02
    Negative Logits
     affor
    -0.94
     attemp
    -0.93
     ?...
    -0.93
     purcha
    -0.93
     encomp
    -0.91
     strick
    -0.90
     increa
    -0.90
     julie
    -0.89
     fortn
    -0.89
     scottish
    -0.88
    POSITIVE LOGITS
     tank
    1.56
     tanks
    1.46
     Tank
    1.45
    Tank
    1.41
    tank
    1.41
     Tanks
    1.24
     TANK
    1.17
    TANK
    1.17
    tanks
    1.10
    Tanks
    1.07
    Activations Density 0.081%

    No Known Activations