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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 450
    Prev
    Next
    INDEX
    Explanations

    names of individuals named Harold

    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
    1407
    +0.13
    0.4%
    795
    +0.10
    0.3%
    314
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.13
    0.06
    1343
    +0.10
    0.05
    1120
    +0.10
    0.05
    Negative Logits
     lamborghini
    -1.01
     dci
    -0.98
     chevrolet
    -0.95
     gsx
    -0.86
     scania
    -0.82
     isuzu
    -0.82
    
    -0.82
     lexus
    -0.80
     hilux
    -0.80
     skoda
    -0.79
    POSITIVE LOGITS
     Harold
    1.19
    Harold
    1.04
     Plymouth
    0.91
    Plymouth
    0.87
     thyroid
    0.80
     Weber
    0.72
     Thyroid
    0.72
     Miguel
    0.70
     camel
    0.69
    thyroid
    0.68
    Activations Density 0.353%

    No Known Activations