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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 643
    Prev
    Next
    INDEX
    Explanations

    phrases related to e-commerce and technical specifications

    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
    +0.22
    0.9%
    1343
    +0.12
    0.5%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1694
    +0.22
    0.08
    1978
    +0.12
    0.13
    1314
    +0.09
    0.10
    Negative Logits
    <bos>
    -4.08
    новништво
    -1.46
    Autoritní
    -1.44
     AssemblyCompany
    -1.31
    HideFlags
    -1.27
    ValueGenerated
    -1.25
    TagMode
    -1.25
    RegressionTest
    -1.24
    Datuak
    -1.20
     autorytatywna
    -1.19
    POSITIVE LOGITS
     increa
    3.30
     affor
    3.23
     reluct
    3.23
     impra
    3.17
     inev
    3.15
     maneu
    3.14
     accla
    3.12
     shenan
    3.11
     disagre
    3.09
     strick
    3.00
    Activations Density 3.166%

    No Known Activations