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. 101
    Prev
    Next
    INDEX
    Explanations

    concepts related to aerobic fitness and oxygen consumption

    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
    228
    +0.14
    0.6%
    1671
    +0.13
    0.6%
    501
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1763
    +0.14
    0.03
    144
    +0.13
    0.03
    1385
    +0.12
    0.03
    Negative Logits
    <bos>
    -1.42
     alre
    -1.18
     encomp
    -1.18
     quitted
    -1.11
     intersper
    -1.08
     attemp
    -1.07
     unve
    -1.03
     impelled
    -1.02
     increa
    -1.02
     amass
    -0.98
    POSITIVE LOGITS
     oxygen
    1.49
    oxygen
    1.40
    Oxygen
    1.25
     Oxygen
    1.25
    XYGEN
    1.09
     oxigen
    1.02
     oxígeno
    0.94
     Sauerstoff
    0.93
    xygen
    0.89
    gruntled
    0.77
    Activations Density 0.306%

    No Known Activations