© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4135
    Prev
    Next
    INDEX
    Explanations

    information related to a specific retailer, particularly Walmart

    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
    1127
    +0.17
    0.9%
    347
    +0.13
    0.7%
    1271
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.17
    0.03
    1097
    +0.13
    0.04
    438
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.60
    ustainable
    -0.56
     guma
    -0.55
     habang
    -0.54
    y
    -0.54
     AppCompatTheme
    -0.53
     torque
    -0.51
     néz
    -0.51
    ീ
    -0.51
     cre
    -0.51
    POSITIVE LOGITS
     Wal
    1.79
    Wal
    1.71
     WAL
    1.40
     wal
    1.27
    WAL
    1.26
     Walton
    1.16
     marte
    1.15
     Leurs
    1.14
     Walther
    1.12
     Sinal
    1.11
    Activations Density 0.291%

    No Known Activations