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. 14809
    Prev
    Next
    INDEX
    Explanations

    terms related to amenities and services offered in a vacation rental property or hotel

    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
    950
    +0.14
    0.8%
    1416
    +0.14
    0.7%
    1896
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    144
    +0.14
    0.04
    1896
    +0.14
    0.04
    950
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.70
    CloseOperation
    -0.74
     poveznice
    -0.65
     izvē
    -0.64
    MergeFrom
    -0.63
    ItemBackground
    -0.63
     қара
    -0.61
     informée
    -0.60
    Anhalt
    -0.60
    ActionMode
    -0.60
    POSITIVE LOGITS
     increa
    1.13
     GIP
    1.10
     curé
    1.07
    Wi
    1.05
     Winf
    1.03
     unden
    1.03
     habile
    1.02
     Intere
    1.02
     inev
    1.01
     disreg
    1.01
    Activations Density 0.441%

    No Known Activations