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. 3292
    Prev
    Next
    INDEX
    Explanations

    phrases related to food items or dishes from different cultures

    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
    +0.19
    0.7%
    1842
    +0.09
    0.3%
    1183
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.19
    0.06
    352
    +0.09
    0.06
    1842
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.69
    पया
    -0.77
     كومونز
    -0.73
    TypedDataSet
    -0.72
    displayquote
    -0.72
    migrationBuilder
    -0.72
     AssemblyCompany
    -0.71
    principalTable
    -0.71
    ParallelGroup
    -0.70
    ValueStyle
    -0.69
    POSITIVE LOGITS
     increa
    2.32
     impra
    2.26
     disagre
    2.23
     inev
    2.23
     thut
    2.19
     emphat
    2.18
     fuf
    2.17
     affor
    2.16
     unden
    2.14
     effe
    2.12
    Activations Density 0.508%

    No Known Activations