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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 742
    Prev
    Next
    INDEX
    Explanations

    actions and decisions related to transactions and personal agency

    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
    +0.15
    0.6%
    678
    +0.13
    0.5%
    1177
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.15
    0.09
    1504
    +0.13
    0.08
    946
    +0.11
    0.07
    Negative Logits
    <bos>
    -2.59
    .
    -0.99
    AfterClass
    -0.91
     also
    -0.89
    ↵↵
    -0.89
    ;
    -0.89
    SizeMode
    -0.88
    ,
    -0.88
    :
    -0.87
    —
    -0.86
    POSITIVE LOGITS
     impra
    2.74
     swarovski
    2.72
     increa
    2.72
     aen
    2.56
     stockholm
    2.55
     thut
    2.55
     emphat
    2.52
     squa
    2.52
     maneu
    2.51
     depic
    2.50
    Activations Density 1.097%

    No Known Activations