© 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. 2017
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific entities or locations, particularly focusing on names that begin with "Wy"

    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
    101
    +0.10
    0.3%
    1406
    +0.10
    0.3%
    662
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.04
    1120
    +0.10
    0.03
    283
    +0.10
    0.01
    Negative Logits
    więks
    -0.81
    więcej
    -0.81
    parseColor
    -0.79
    </tbody>
    -0.78
    bardziej
    -0.78
    ArgsConstructor
    -0.76
    ropical
    -0.71
     Дар
    -0.71
    InternalFrame
    -0.70
    ErrorListener
    -0.70
    POSITIVE LOGITS
     Wy
    2.62
    Wy
    2.31
     effe
    2.11
    wy
    2.01
     nece
    1.99
     WY
    1.96
     sovere
    1.90
     bordeaux
    1.89
     ftu
    1.88
     mef
    1.88
    Activations Density 0.250%

    No Known Activations