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. 9060
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of fraud in financial or legal 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
    1328
    +0.14
    0.7%
    50
    +0.12
    0.6%
    1406
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1328
    +0.14
    0.03
    1896
    +0.12
    0.02
    468
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.32
    rungsseite
    -0.76
     disbur
    -0.62
     Мексичка
    -0.61
     defray
    -0.60
    /*++
    -0.55
    addPreferredGap
    -0.54
     ratify
    -0.53
     disarm
    -0.53
     unblock
    -0.52
    POSITIVE LOGITS
     Fraud
    1.19
     fraud
    1.19
    Fraud
    1.13
    fraud
    1.12
     Luglio
    0.91
     tantôt
    0.90
     quelquefois
    0.89
     senhora
    0.84
     aussitôt
    0.84
     volon
    0.82
    Activations Density 0.288%

    No Known Activations