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. 6200
    Prev
    Next
    INDEX
    Explanations

    references to different types of utensils and kitchen supplies

    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
    313
    +0.19
    1.0%
    1296
    +0.18
    1.0%
    1492
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.19
    0.05
    1741
    +0.18
    -0.01
    478
    +0.15
    0.02
    Negative Logits
    <bos>
    -1.02
    提
    -0.60
    bot
    -0.59
    bo
    -0.58
    Đặc
    -0.56
    pub
    -0.56
    бо
    -0.55
    栗
    -0.54
     bo
    -0.54
    case
    -0.54
    POSITIVE LOGITS
     Khart
    1.09
     ftu
    1.04
     Juf
    1.02
     unwarran
    1.01
     centrif
    1.00
     paradiso
    1.00
     tranf
    1.00
     anhyd
    0.99
     fta
    0.99
     oleo
    0.99
    Activations Density 0.847%

    No Known Activations