© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1202
    Prev
    Next
    INDEX
    Explanations

    words related to cocktails and beverages

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    805
    +0.10
    0.3%
    1306
    +0.09
    0.3%
    1575
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    783
    +0.10
    0.03
    823
    +0.09
    0.03
    690
    +0.09
    0.03
    Negative Logits
    WriteAttribute
    -0.67
    ForValue
    -0.65
    LayoutStyle
    -0.63
    featureID
    -0.60
    __;
    -0.60
    }());
    -0.58
    kaŭ
    -0.58
    awtextra
    -0.58
    __":
    -0.57
    IonicModule
    -0.56
    POSITIVE LOGITS
     cocktail
    2.07
     Cocktail
    1.92
    cocktail
    1.81
    Cocktail
    1.74
     cocktails
    1.69
     Cocktails
    1.43
     ftu
    1.36
     vns
    1.35
     mef
    1.33
     aen
    1.32
    Activations Density 0.269%

    No Known Activations