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. 9132
    Prev
    Next
    INDEX
    Explanations

    countries or places mentioned in financial or economic contexts

    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
    370
    +0.14
    0.6%
    866
    +0.14
    0.6%
    1103
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.14
    0.05
    438
    +0.14
    0.04
    200
    +0.13
    0.04
    Negative Logits
    <bos>
    -1.26
    SequentialGroup
    -0.68
    })();
    
    -0.63
    RepeatedField
    -0.63
    ParallelGroup
    -0.59
    matchCondition
    -0.58
    BoxShadow
    -0.58
    cshtml
    -0.57
    حوالہ
    -0.55
     consultato
    -0.55
    POSITIVE LOGITS
     Jamaican
    1.16
     carrefour
    1.15
     Jamaica
    1.09
     pavillon
    1.09
     Caribbean
    1.04
     pymysql
    1.02
     clô
    1.02
     plancher
    1.00
     velours
    0.99
     bourg
    0.96
    Activations Density 0.433%

    No Known Activations