© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 982
    Prev
    Next
    INDEX
    Explanations

    phrases indicating action, intention, or observation

    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
    +0.23
    1.1%
    1026
    +0.12
    0.6%
    1140
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1026
    +0.23
    0.06
    1334
    +0.12
    0.05
    869
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.82
     intersper
    -1.23
     endow
    -0.94
    /***
    -0.92
    ⓧ
    -0.91
     strove
    -0.81
    <?
    -0.81
     endeavored
    -0.81
     harmonize
    -0.78
     disambigu
    -0.78
    POSITIVE LOGITS
    braith
    0.80
    lijah
    0.76
    GYPT
    0.74
    lindo
    0.74
     jawa
    0.73
    naldo
    0.71
    wahati
    0.70
     Muhamma
    0.70
    capulco
    0.69
    quarelle
    0.67
    Activations Density 0.302%

    No Known Activations