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. 10-RES-JB
    6. 6778
    Prev
    Next
    INDEX
    Explanations

    terms related to human ancestry and migration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.26
    1.0%
    1842
    +0.12
    0.5%
    752
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.26
    0.06
    736
    +0.12
    0.05
    945
    +0.11
    0.05
    Negative Logits
    <bos>
    -1.86
    Autoritní
    -0.71
    webElementXpaths
    -0.59
    public
    -0.59
     consult
    -0.55
     manage
    -0.54
     will
    -0.54
     inform
    -0.53
     subscribe
    -0.53
     are
    -0.52
    POSITIVE LOGITS
     ftu
    1.66
     thut
    1.62
     perfon
    1.60
     reft
    1.59
     ftre
    1.57
     effe
    1.54
     desir
    1.53
     nece
    1.52
     fta
    1.46
     fto
    1.46
    Activations Density 0.619%

    No Known Activations