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. 6-RES-JB
    6. 6111
    Prev
    Next
    INDEX
    Explanations

    real estate property details such as price, location, and dimensions

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.0%
    453
    +0.15
    0.6%
    1253
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.26
    0.10
    1445
    +0.15
    0.08
    1419
    +0.11
    0.05
    Negative Logits
    <bos>
    -2.43
    ⓧ
    -0.76
     introduce
    -0.75
     put
    -0.73
     reduce
    -0.72
    <?
    -0.71
     raise
    -0.70
    Хро
    -0.70
     adapt
    -0.70
    /**
    -0.70
    POSITIVE LOGITS
     napoli
    1.92
     accla
    1.89
     madonna
    1.87
     peppa
    1.84
     wien
    1.82
     milano
    1.80
     affor
    1.80
     stockholm
    1.77
     embra
    1.75
     applau
    1.73
    Activations Density 1.237%

    No Known Activations