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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 878
    Prev
    Next
    INDEX
    Explanations

    references to heat and thermal-related terms

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.2%
    101
    +0.12
    0.7%
    67
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.19
    0.04
    101
    +0.12
    0.03
    1233
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.20
    ⓧ
    -0.94
    /**
    -0.76
    glPushMatrix
    -0.75
    <?
    -0.74
    /*
    -0.71
    
    
    -0.70
    glMatrixMode
    -0.69
    glTranslatef
    -0.67
    fileprivate
    -0.64
    POSITIVE LOGITS
     maneu
    1.73
     impra
    1.68
     Juf
    1.60
     beverly
    1.60
     wien
    1.59
     emphat
    1.58
     affor
    1.57
     bandung
    1.57
     disagre
    1.56
     increa
    1.55
    Activations Density 0.063%

    No Known Activations