© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 1058
    Prev
    Next
    INDEX
    Explanations

    terms related to atoms

    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
    1942
    +0.10
    0.3%
    1323
    +0.09
    0.3%
    1306
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1853
    +0.10
    0.02
    1363
    +0.09
    0.02
    1949
    +0.09
    0.02
    Negative Logits
    public
    -0.72
      
    -0.67
     ви
    -0.66
     bring
    -0.66
    нулась
    -0.66
    DriverManager
    -0.66
            
    -0.66
    ・
    -0.65
        
    -0.64
     بال
    -0.64
    POSITIVE LOGITS
     Atom
    2.75
     atom
    2.70
    Atom
    2.55
     ATOM
    2.48
     Atoms
    2.40
     atomic
    2.37
     Atomic
    2.32
     atoms
    2.31
    atom
    2.23
    Atomic
    2.19
    Activations Density 0.251%

    No Known Activations