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. 1244
    Prev
    Next
    INDEX
    Explanations

    concepts related to resource allocation and management

    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
    +0.24
    0.9%
    1385
    +0.12
    0.4%
    1224
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.24
    0.06
    1745
    +0.12
    0.04
    876
    +0.08
    -0.02
    Negative Logits
    <bos>
    -2.00
     intersper
    -1.03
     enshr
    -0.93
     underval
    -0.88
     endeavored
    -0.84
     acquaint
    -0.80
     vanqu
    -0.80
     endeavoured
    -0.80
     encomp
    -0.79
     apprehen
    -0.78
    POSITIVE LOGITS
     cias
    0.83
     churrasco
    0.79
    seigneur
    0.78
     pimiento
    0.78
     resources
    0.77
     jawa
    0.75
     palio
    0.74
     bandung
    0.74
     chiesto
    0.74
     asado
    0.73
    Activations Density 0.374%

    No Known Activations