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. 6073
    Prev
    Next
    INDEX
    Explanations

    specific references to a particular place or location

    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
    1.2%
    1757
    +0.10
    0.6%
    421
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    814
    +0.20
    0.05
    1491
    +0.10
    0.04
    421
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.46
    contentLoaded
    -0.60
     modernize
    -0.60
    //---
    -0.60
     adjust
    -0.59
     rehabilitate
    -0.58
    <?
    -0.58
    /*++
    -0.58
     lift
    -0.57
    public
    -0.55
    POSITIVE LOGITS
     maroc
    1.25
     ecru
    1.22
     ankara
    1.20
     bordeaux
    1.18
     seksi
    1.09
     swarovski
    1.08
     cartier
    1.08
     hairc
    1.08
     palio
    1.07
     milano
    1.07
    Activations Density 0.146%

    No Known Activations