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. 752
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, such as cities and regions

    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
    1909
    +0.18
    1.0%
    1708
    +0.17
    0.9%
    1271
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.18
    0.04
    1328
    +0.17
    0.04
    1343
    +0.13
    0.06
    Negative Logits
    <bos>
    -1.11
    OGND
    -0.87
    Đối
    -0.79
    Hozzáférés
    -0.75
    selaer
    -0.69
    حياته
    -0.64
    Phân
    -0.64
    حياتها
    -0.64
    MessageTagHelper
    -0.63
    htbp
    -0.63
    POSITIVE LOGITS
     increa
    1.59
     inev
    1.53
     madonna
    1.51
     fta
    1.51
     ftu
    1.49
     affor
    1.47
     thut
    1.47
     emphat
    1.46
     coö
    1.46
     alre
    1.43
    Activations Density 0.521%

    No Known Activations