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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 15110
    Prev
    Next
    INDEX
    Explanations

    references to financial status and familial background

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    509
    +0.11
    0.3%
    674
    +0.10
    0.3%
    1533
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.11
    0.06
    1260
    +0.10
    0.01
    1533
    +0.10
    0.02
    Negative Logits
     wien
    -1.80
     increa
    -1.78
     unden
    -1.77
     inev
    -1.73
     maneu
    -1.71
     affor
    -1.70
     wherea
    -1.69
     „,
    -1.68
     mef
    -1.68
     impra
    -1.67
    POSITIVE LOGITS
    <bos>
    0.96
     AssemblyCompany
    0.74
    ParallelGroup
    0.71
    GraphicsUnit
    0.67
     dad
    0.66
    RTDA
    0.66
    xase
    0.65
     father
    0.63
    setViewName
    0.62
    父
    0.61
    Activations Density 0.430%

    No Known Activations