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. 1800
    Prev
    Next
    INDEX
    Explanations

    keywords related to the age of individuals, particularly youth

    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
    +0.25
    1.0%
    1978
    +0.14
    0.6%
    1244
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.25
    0.04
    231
    +0.14
    0.04
    1244
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.26
    
    -0.69
    /*
    -0.68
    Autoritní
    -0.68
    FunctionFlags
    -0.66
     invokingState
    -0.65
    ⓧ
    -0.65
    }],
    
    -0.63
    khó
    -0.63
     مرئيه
    -0.63
    POSITIVE LOGITS
     Khart
    1.30
     Bartholo
    1.28
     reluct
    1.26
     Juf
    1.19
     maneu
    1.16
     Middles
    1.16
     juven
    1.15
     Ruman
    1.14
     accla
    1.14
     Hez
    1.11
    Activations Density 0.100%

    No Known Activations