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. 208
    Prev
    Next
    INDEX
    Explanations

    terms related to free agency in sports

    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
    1531
    +0.06
    0.2%
    1615
    +0.06
    0.2%
    1620
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1884
    +0.06
    0.03
    1891
    +0.06
    0.04
    1531
    +0.06
    0.03
    Negative Logits
    addComponent
    -0.73
    push
    -0.67
    ღ
    -0.66
     lấy
    -0.65
    link
    -0.65
    lang
    -0.64
    addGroup
    -0.64
    protected
    -0.64
    comp
    -0.64
    ਾਲ
    -0.64
    POSITIVE LOGITS
     maneu
    2.27
     disagre
    2.05
     guarante
    1.92
     increa
    1.90
     accla
    1.89
     carrefour
    1.82
     gaily
    1.82
     excru
    1.81
     ftu
    1.80
     wherea
    1.80
    Activations Density 0.406%

    No Known Activations