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. 1007
    Prev
    Next
    INDEX
    Explanations

    references to torture

    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
    +0.22
    1.2%
    757
    +0.12
    0.6%
    1565
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.22
    0.01
    1565
    +0.12
    0.01
    1910
    +0.09
    0.01
    Negative Logits
    <bos>
    -3.24
    jsii
    -0.70
    Autoritní
    -0.70
    displayquote
    -0.69
    else
    -0.68
    public
    -0.67
     AssemblyCompany
    -0.67
    setClass
    -0.65
    SequentialGroup
    -0.65
    sizeCache
    -0.63
    POSITIVE LOGITS
     pymysql
    1.58
     ecru
    1.57
     swarovski
    1.51
     Minang
    1.50
     Juf
    1.48
     tolerably
    1.46
     hcm
    1.37
     carrefour
    1.35
     unwarran
    1.35
     murano
    1.31
    Activations Density 0.020%

    No Known Activations