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. 930
    Prev
    Next
    INDEX
    Explanations

    mentions of sports events and achievements

    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%
    736
    +0.08
    0.3%
    1842
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.20
    0.04
    736
    +0.08
    0.04
    1823
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.32
    UnknownFieldSet
    -0.69
     censiti
    -0.69
    mergeFrom
    -0.65
     SEDS
    -0.63
    ariums
    -0.63
    <>
    
    -0.59
    Geplaatst
    -0.59
    YMS
    -0.58
    beros
    -0.58
    POSITIVE LOGITS
     maneu
    1.77
     affor
    1.68
     snoopy
    1.61
     accla
    1.60
     michelin
    1.58
     increa
    1.58
     impra
    1.56
     fortn
    1.56
     depic
    1.53
     milf
    1.52
    Activations Density 0.245%

    No Known Activations