Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 32
    Prev
    Next
    INDEX
    Explanations

    references to Triple-A sports leagues

    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
    1472
    +0.10
    0.3%
    1092
    +0.08
    0.3%
    479
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1490
    +0.10
    0.03
    78
    +0.08
    0.03
    1242
    +0.07
    0.03
    Negative Logits
    else
    -0.65
    public
    -0.65
    //};
    -0.64
    int
    -0.64
     do
    -0.63
    beta
    -0.62
    자
    -0.62
     den
    -0.62
    protected
    -0.62
    ു
    -0.61
    POSITIVE LOGITS
     Triple
    2.60
    Triple
    2.50
     triple
    2.46
    triple
    2.45
     quadruple
    2.17
     accla
    2.08
     increa
    2.05
     strick
    1.98
     triples
    1.97
     stockholm
    1.96
    Activations Density 0.203%

    No Known Activations