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. 749
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months and time periods

    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
    1.0%
    1045
    +0.09
    0.5%
    950
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1045
    +0.20
    0.06
    147
    +0.09
    0.05
    776
    +0.08
    0.08
    Negative Logits
    <bos>
    -3.43
    ⓧ
    -0.93
    ItemBackground
    -0.76
    ///**
    -0.72
    def
    -0.72
    writeField
    -0.71
    AsUp
    -0.71
    WriteHeader
    -0.71
    define
    -0.70
    MergeFrom
    -0.70
    POSITIVE LOGITS
     stockholm
    1.79
     fta
    1.78
     maneu
    1.75
     ftu
    1.75
     riviera
    1.74
     madonna
    1.74
     fays
    1.72
     unwarran
    1.70
     reft
    1.67
     Confu
    1.66
    Activations Density 0.364%

    No Known Activations