Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 197
    Prev
    Next
    INDEX
    Explanations

    short time-related phrases

    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
    +0.20
    0.9%
    31
    +0.11
    0.5%
    341
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1105
    +0.20
    0.05
    1984
    +0.11
    0.06
    31
    +0.10
    0.05
    Negative Logits
    <bos>
    -2.48
     kasarigan
    -0.68
    商品説明
    -0.63
    IActionResult
    -0.62
    },[])
    -0.60
    Puis
    -0.59
    elemField
    -0.58
    VIAF
    -0.58
     defStyleAttr
    -0.58
    uxxxx
    -0.57
    POSITIVE LOGITS
     délib
    1.07
     sappi
    1.05
     aveug
    0.96
     bourg
    0.96
     accla
    0.95
     cartier
    0.93
     véhic
    0.92
     Lycée
    0.92
     maneu
    0.92
     pavillon
    0.92
    Activations Density 0.673%

    No Known Activations