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. 807
    Prev
    Next
    INDEX
    Explanations

    instances of the word "released" and its variations, indicating referrals to freedom or liberation

    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
    +0.27
    0.9%
    1013
    +0.10
    0.3%
    690
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.27
    0.05
    1013
    +0.10
    0.07
    509
    +0.07
    0.06
    Negative Logits
    <bos>
    -1.98
     intersper
    -1.08
    
    
    -0.94
     endow
    -0.89
    /***
    
    -0.84
     underval
    -0.81
    ⓧ
    -0.78
     endeavored
    -0.76
    <?
    
    -0.76
     enshr
    -0.74
    POSITIVE LOGITS
    MLLoader
    0.73
     WaitForSeconds
    0.69
    hdas
    0.67
    requipa
    0.66
    °;
    0.65
     GoogleFonts
    0.65
    échal
    0.65
     Himo
    0.64
     ianuarie
    0.64
     montagna
    0.63
    Activations Density 0.594%

    No Known Activations