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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 128
    Prev
    Next
    INDEX
    Explanations

    descriptions of clothing items and their materials

    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
    +0.28
    1.0%
    1385
    +0.14
    0.5%
    297
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.28
    0.10
    583
    +0.14
    0.05
    1603
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.10
    /***
    
    -0.68
    ///**
    -0.60
     springfox
    -0.58
    ⓧ
    -0.58
    public
    -0.57
    HomeAsUpEnabled
    -0.54
     mobilize
    -0.53
    刺繍
    -0.53
    <tfoot>
    -0.52
    POSITIVE LOGITS
     soulign
    1.23
     maneu
    1.13
     affor
    1.11
     plong
    1.08
     Keny
    1.07
     Juf
    1.07
     stockholm
    1.03
     accla
    1.03
     volunte
    1.01
     affez
    0.99
    Activations Density 0.673%

    No Known Activations