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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14497
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions for a soup recipe

    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
    0.7%
    1013
    +0.13
    0.5%
    1177
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.20
    0.06
    1551
    +0.13
    0.04
    594
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.09
    ⓧ
    -0.69
    <!--
    
    -0.59
    CreateIndex
    -0.57
    })();
    
    -0.54
    <?
    
    -0.54
     repatri
    -0.54
    usercontent
    -0.53
    ScopeManager
    -0.53
     AssemblyCompany
    -0.52
    POSITIVE LOGITS
     Juf
    1.16
     aen
    1.08
     glau
    1.06
     maer
    1.06
     anhyd
    1.02
     pollut
    0.98
     meis
    0.95
     ftu
    0.95
     jaya
    0.93
     blackish
    0.93
    Activations Density 0.254%

    No Known Activations