© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1023
    Prev
    Next
    INDEX
    Explanations

    the word "wing."

    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
    32
    +0.09
    0.3%
    1548
    +0.08
    0.3%
    1491
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.09
    0.03
    960
    +0.08
    0.03
    1548
    +0.07
    0.02
    Negative Logits
    protected
    -0.78
    public
    -0.73
    <bos>
    -0.70
    private
    -0.67
    abetes
    -0.67
    blico
    -0.67
     للاسماء
    -0.66
    autorest
    -0.66
    IEnumerator
    -0.64
    export
    -0.64
    POSITIVE LOGITS
     wing
    2.71
     wings
    2.51
     Wing
    2.40
     WING
    2.36
    Wing
    2.29
    wings
    2.11
     Wings
    2.07
    wing
    2.02
     affor
    1.97
    Wings
    1.96
    Activations Density 0.175%

    No Known Activations