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. 20
    Prev
    Next
    INDEX
    Explanations

    names of places or entities

    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
    381
    +0.21
    1.1%
    1535
    +0.14
    0.8%
    297
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.21
    0.11
    1343
    +0.14
    0.11
    1056
    +0.13
    0.09
    Negative Logits
    <bos>
    -2.06
     sindaco
    -0.99
     giudice
    -0.90
     papà
    -0.88
    /**
    -0.87
    ⓧ
    -0.83
     signore
    -0.79
     nemico
    -0.78
     fidanz
    -0.76
     zöld
    -0.76
    POSITIVE LOGITS
     compréhen
    1.51
     quoique
    1.41
     délib
    1.39
     prouve
    1.38
     éto
    1.36
     véhic
    1.34
     soulign
    1.34
     rafra
    1.33
     prétend
    1.31
     renfer
    1.31
    Activations Density 0.801%

    No Known Activations