© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 217
    Prev
    Next
    INDEX
    Explanations

    instances of fading effects or processes

    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
    82
    +0.09
    0.3%
    1909
    +0.09
    0.3%
    1757
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.03
    1450
    +0.09
    0.02
    1896
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.20
    /***
    -0.54
     насеља
    -0.50
    
    -0.50
    char
    -0.49
    stock
    -0.48
    public
    -0.48
    DataPropertyName
    -0.47
     /**
    -0.47
    fran
    -0.47
    POSITIVE LOGITS
     fade
    2.22
     fading
    2.11
     fades
    1.96
     faded
    1.96
     decay
    1.86
     Fade
    1.73
    fade
    1.64
     decaying
    1.60
     decayed
    1.59
     decays
    1.57
    Activations Density 0.156%

    No Known Activations