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. 145
    Prev
    Next
    INDEX
    Explanations

    numeric values associated with dimensions such as height and width

    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
    0.3%
    1387
    +0.07
    0.2%
    544
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1218
    +0.09
    0.03
    1614
    +0.07
    0.03
    1387
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.36
    
    
    -0.97
    ⓧ
    -0.90
    <?
    -0.87
    /**
    -0.79
    /*
    -0.76
     shuddered
    -0.64
    <?
    
    -0.63
    #
    -0.63
     overtook
    -0.62
    POSITIVE LOGITS
     height
    1.72
     Height
    1.56
    height
    1.52
     width
    1.46
     heights
    1.43
    Height
    1.41
     Width
    1.37
     HEIGHT
    1.32
     maroc
    1.31
    width
    1.31
    Activations Density 0.110%

    No Known Activations