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. 0-RES-JB
    6. 35
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical density or population density in a city or area

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    871
    +0.10
    0.3%
    896
    +0.09
    0.3%
    1491
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    127
    +0.10
    0.02
    871
    +0.09
    0.02
    251
    +0.09
    0.02
    Negative Logits
    parent
    -0.53
     Martin
    -0.52
    Martin
    -0.49
     Childs
    -0.49
     Wade
    -0.48
     Kirk
    -0.48
     Parent
    -0.48
     fund
    -0.47
    врат
    -0.47
    ="#"><
    -0.47
    POSITIVE LOGITS
     density
    2.99
     Density
    2.92
    density
    2.83
     densities
    2.72
    Density
    2.62
     dense
    2.43
     denser
    2.31
     DENSITY
    2.31
    dense
    2.14
     Dense
    2.13
    Activations Density 0.173%

    No Known Activations