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. 14852
    Prev
    Next
    INDEX
    Explanations

    mentions of mesh material or mesh-related features in a product description

    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
    1296
    +0.22
    1.0%
    1677
    +0.17
    0.8%
    1573
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.22
    0.06
    1677
    +0.17
    0.03
    690
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.16
    Abril
    -0.63
    VisualStudio
    -0.60
    Mí
    -0.57
    Már
    -0.56
    BeginInit
    -0.56
    glPopMatrix
    -0.56
    glLoad
    -0.55
    nsan
    -0.53
     dez
    -0.53
    POSITIVE LOGITS
     mesh
    1.11
    mesh
    0.99
     meshes
    0.97
     Mesh
    0.95
     muna
    0.91
    Mesh
    0.90
     thut
    0.88
     hentai
    0.88
    MESH
    0.88
     hanggang
    0.88
    Activations Density 0.355%

    No Known Activations