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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 286
    Prev
    Next
    INDEX
    Explanations

    references to workers or workplaces

    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
    50
    +0.09
    0.4%
    1350
    +0.07
    0.3%
    1865
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1040
    +0.09
    0.05
    1865
    +0.07
    0.04
    1109
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.26
    <?
    -0.79
    
    
    -0.76
    /*
    -0.74
    const
    -0.69
    public
    -0.68
    #
    -0.67
    /**
    -0.67
    void
    -0.66
    ⓧ
    -0.65
    POSITIVE LOGITS
     maneu
    1.85
     affor
    1.85
     emphat
    1.83
     increa
    1.81
     Workers
    1.80
     worker
    1.80
     workers
    1.79
     stockholm
    1.79
     impra
    1.74
     Worker
    1.73
    Activations Density 0.111%

    No Known Activations