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. 500
    Prev
    Next
    INDEX
    Explanations

    references to LEGO-related content

    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
    298
    +0.11
    0.4%
    1052
    +0.11
    0.4%
    68
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.11
    0.06
    1987
    +0.11
    0.06
    1741
    +0.11
    0.01
    Negative Logits
     blackpink
    -0.74
    RectangleBorder
    -0.70
    šech
    -0.64
    oplasmic
    -0.60
    ⓧ
    -0.59
    xFFFFFF
    -0.58
    xffffff
    -0.56
    relenting
    -0.56
    ostruct
    -0.55
    itschrift
    -0.53
    POSITIVE LOGITS
     Augu
    0.97
     allarg
    0.96
     Mlle
    0.90
     affari
    0.87
     dispen
    0.86
     abbra
    0.86
     Godt
    0.85
     doman
    0.85
     §.
    0.84
     effe
    0.83
    Activations Density 0.436%

    No Known Activations