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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14547
    Prev
    Next
    INDEX
    Explanations

    obituaries or tribute information

    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
    +0.26
    1.0%
    1548
    +0.07
    0.3%
    855
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1214
    +0.26
    0.05
    402
    +0.07
    0.06
    1203
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.25
     prepare
    -0.58
     rehabilitate
    -0.58
     adopt
    -0.57
     regulate
    -0.56
     intensify
    -0.55
     stabilize
    -0.54
     straighten
    -0.54
    ///**
    -0.54
     apply
    -0.54
    POSITIVE LOGITS
     Juf
    1.27
     Minang
    1.26
     véhic
    1.20
     Khart
    1.19
     Augu
    1.09
     Muhamma
    1.09
     sovere
    1.08
     soulign
    1.08
     Seni
    1.05
     fua
    1.04
    Activations Density 0.628%

    No Known Activations