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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 13
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to sports teams or individuals

    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
    1557
    +0.10
    0.3%
    161
    +0.10
    0.3%
    492
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.05
    690
    +0.10
    0.05
    1363
    +0.09
    0.04
    Negative Logits
     jeste
    -0.65
     tager
    -0.62
     findes
    -0.61
    مد
    -0.60
    larımız
    -0.59
    зидент
    -0.59
    paralleled
    -0.59
     participate
    -0.58
     receive
    -0.58
    oblotting
    -0.57
    POSITIVE LOGITS
     Kn
    1.95
    Kn
    1.77
     kn
    1.61
     embra
    1.48
     effe
    1.46
     eiffel
    1.46
     campa
    1.46
     depic
    1.44
     accla
    1.44
     unden
    1.43
    Activations Density 0.317%

    No Known Activations