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. 3053
    Prev
    Next
    INDEX
    Explanations

    information related to financial investments and risk analysis

    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
    1978
    +0.09
    0.3%
    1804
    +0.07
    0.2%
    1888
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1888
    +0.09
    0.05
    455
    +0.07
    0.02
    1260
    +0.07
    0.01
    Negative Logits
     Juf
    -1.22
     Keny
    -1.17
     fluo
    -1.14
     mef
    -1.12
     levis
    -1.07
     affez
    -1.07
     ivi
    -1.06
     bres
    -1.03
     Sted
    -1.02
     dises
    -1.01
    POSITIVE LOGITS
     varies
    1.01
     depends
    0.92
     differs
    0.85
     exceeds
    0.80
     vary
    0.79
     seems
    0.79
     is
    0.78
     was
    0.75
     varied
    0.74
     remains
    0.72
    Activations Density 0.471%

    No Known Activations