© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    phrases related to directives or commands

    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
    +0.27
    1.3%
    1974
    +0.13
    0.6%
    1381
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.27
    0.03
    1974
    +0.13
    0.05
    1506
    +0.12
    0.06
    Negative Logits
    <bos>
    -2.20
    <?
    -0.76
    ⓧ
    -0.73
    
    -0.63
    /***
    -0.59
     endow
    -0.56
    /**
    -0.53
    Aholisi
    -0.52
     /**
    -0.51
    else
    -0.50
    POSITIVE LOGITS
     potest
    0.93
     letti
    0.92
     inol
    0.91
     tramont
    0.90
     nomine
    0.89
     viciss
    0.85
     riva
    0.85
     practition
    0.85
     chicco
    0.84
     palio
    0.84
    Activations Density 1.614%

    No Known Activations