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. 572
    Prev
    Next
    INDEX
    Explanations

    mentions of specific types of home building materials, specifically tiles

    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
    82
    +0.16
    0.8%
    1262
    +0.14
    0.7%
    1961
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.16
    0.05
    1013
    +0.14
    0.04
    690
    +0.14
    0.03
    Negative Logits
    <bos>
    -1.27
     كومونز
    -0.75
     Perci
    -0.74
     encomp
    -0.74
     Molto
    -0.73
     Più
    -0.73
     springfox
    -0.72
     Stretcher
    -0.71
     Abbiamo
    -0.70
     Altri
    -0.70
    POSITIVE LOGITS
     tile
    1.48
     tiles
    1.40
    Tile
    1.29
     Tile
    1.27
    tile
    1.24
    Tiles
    1.22
    tiles
    1.14
     Tiles
    1.07
    TILE
    1.06
     tiled
    1.03
    Activations Density 0.395%

    No Known Activations