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. 167
    Prev
    Next
    INDEX
    Explanations

    contact information, including addresses, phone numbers, and email addresses

    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
    +0.24
    1.1%
    2034
    +0.07
    0.3%
    382
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.24
    0.04
    1123
    +0.07
    0.03
    1903
    +0.06
    0.03
    Negative Logits
    <bos>
    -2.02
    ⓧ
    -1.20
     intersper
    -1.09
     gratify
    -1.04
    /**
    -0.99
    
    
    -0.97
     disbur
    -0.96
    /***
    
    -0.94
    <?
    
    -0.90
     forbear
    -0.89
    POSITIVE LOGITS
    :].
    0.57
    abancı
    0.55
     catég
    0.54
     alté
    0.54
     Kanada
    0.52
     seksi
    0.51
     balon
    0.50
    UITextField
    0.50
     polizia
    0.49
     Teknik
    0.49
    Activations Density 0.073%

    No Known Activations