© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 3508
    Prev
    Next
    INDEX
    Explanations

    financial market information related to point changes in stock market indices and percentage changes in oil prices

    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
    0.9%
    1445
    +0.08
    0.3%
    453
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1445
    +0.24
    0.05
    439
    +0.08
    0.04
    1265
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.67
     intersper
    -1.06
    <?
    -1.03
    ⓧ
    -1.01
    
    -0.99
     quitted
    -0.97
    /**
    -0.90
     endeavored
    -0.82
     endeavoured
    -0.79
     disbur
    -0.77
    POSITIVE LOGITS
     jawa
    0.85
     santiago
    0.77
     jaya
    0.77
     Praça
    0.76
     bosco
    0.74
     bandung
    0.74
     palio
    0.74
     paradiso
    0.73
     maroc
    0.71
     Redacción
    0.70
    Activations Density 0.240%

    No Known Activations