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. 14772
    Prev
    Next
    INDEX
    Explanations

    legal terms and details related to a purchase agreement

    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
    1350
    +0.20
    1.1%
    874
    +0.17
    0.9%
    1053
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.20
    0.04
    1350
    +0.17
    0.04
    1097
    +0.17
    0.05
    Negative Logits
    <bos>
    -0.95
    Mob
    -0.59
    PerformLayout
    -0.58
     Mob
    -0.57
    ฺ
    -0.55
     Normdatei
    -0.55
    깝
    -0.51
     Perez
    -0.51
    Cá
    -0.51
     chip
    -0.51
    POSITIVE LOGITS
     tupperware
    0.94
     nutella
    0.93
     tarte
    0.90
     pimiento
    0.82
     eiffel
    0.81
     thermomix
    0.78
     réunis
    0.77
     mascarpone
    0.76
     pican
    0.76
     oreo
    0.74
    Activations Density 0.617%

    No Known Activations