© 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. 210
    Prev
    Next
    INDEX
    Explanations

    words related to sound and audio

    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
    50
    +0.11
    0.5%
    1296
    +0.07
    0.3%
    1671
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.11
    0.05
    258
    +0.07
    0.04
    1372
    +0.06
    0.04
    Negative Logits
    <bos>
    -1.96
    ⓧ
    -0.86
    public
    -0.79
    .
    -0.74
    displayquote
    -0.74
    ,
    -0.74
    util
    -0.70
     continue
    -0.70
    HasIndex
    -0.70
    itemize
    -0.70
    POSITIVE LOGITS
     maneu
    2.02
     accla
    1.97
     affor
    1.97
     ftu
    1.94
     increa
    1.91
     hcm
    1.91
     stockholm
    1.89
     emphat
    1.89
     impra
    1.88
     fta
    1.87
    Activations Density 0.094%

    No Known Activations