Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5821
    Prev
    Next
    INDEX
    Explanations

    terms related to sailing and wind activities

    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
    +0.10
    0.4%
    1407
    +0.10
    0.4%
    410
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.10
    0.02
    1691
    +0.10
    0.02
    690
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.22
    fjspx
    -0.81
    <?
    -0.76
     Normdatei
    -0.76
    queryInterface
    -0.74
    awtextra
    -0.73
    /*++
    -0.73
    ⓧ
    -0.71
    ftagPool
    -0.68
    mergeFrom
    -0.67
    POSITIVE LOGITS
     impra
    1.57
     increa
    1.57
     Minang
    1.56
     affor
    1.53
     accla
    1.53
     bandung
    1.51
     jaya
    1.51
     uninten
    1.50
     swarovski
    1.50
     Juf
    1.50
    Activations Density 0.214%

    No Known Activations