Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 165
    Prev
    Next
    INDEX
    Explanations

    locations or events related to community and local news

    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
    1562
    +0.07
    0.2%
    211
    +0.07
    0.2%
    156
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.07
    0.02
    931
    +0.07
    0.02
    30
    +0.07
    0.02
    Negative Logits
    ingual
    -0.64
    ⓧ
    -0.63
     AssemblyCompany
    -0.61
    fristi
    -0.61
     lại
    -0.61
     boost
    -0.60
     specialize
    -0.59
     pulled
    -0.59
     specializes
    -0.59
     promote
    -0.59
    POSITIVE LOGITS
     Mt
    2.18
     Mount
    1.99
    Mt
    1.92
     maneu
    1.70
     Juf
    1.68
    Mount
    1.67
     affor
    1.51
     casio
    1.50
     impra
    1.49
     confé
    1.49
    Activations Density 0.238%

    No Known Activations