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. 544
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and medications, specifically focusing on cholesterol-lowering drugs

    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
    +0.30
    1.4%
    1590
    +0.06
    0.3%
    1705
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.30
    0.11
    1013
    +0.06
    0.25
    783
    +0.06
    0.15
    Negative Logits
    <bos>
    -1.42
    .
    -0.98
    ,
    -0.91
    <eos>
    -0.89
    ;
    -0.87
     put
    -0.85
     also
    -0.85
     provide
    -0.84
     both
    -0.84
     do
    -0.84
    POSITIVE LOGITS
     Juf
    2.52
     sovere
    2.37
     Minang
    2.29
     bandung
    2.24
     emphat
    2.19
     maneu
    2.19
     Intere
    2.18
     inev
    2.17
     stockholm
    2.17
     affor
    2.16
    Activations Density 6.195%

    No Known Activations