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. 15728
    Prev
    Next
    INDEX
    Explanations

    details related to economics such as pricing policies and international trade impacts

    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
    381
    +0.14
    0.5%
    1978
    +0.13
    0.4%
    1967
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1804
    +0.14
    0.06
    1719
    +0.13
    0.05
    1665
    +0.13
    0.04
    Negative Logits
     unspeak
    -1.19
     indescri
    -1.09
     ruddy
    -1.09
     melange
    -1.08
     shenan
    -1.07
     horrend
    -1.03
     pooh
    -1.01
     wolverine
    -1.00
     chattering
    -1.00
     thoughtless
    -0.98
    POSITIVE LOGITS
     alkoh
    2.28
     silikon
    2.25
     karton
    2.24
     utop
    2.12
     solidar
    2.12
     keramik
    2.11
     minimalis
    2.09
     kosme
    2.08
     keram
    2.02
     stoff
    2.02
    Activations Density 0.274%

    No Known Activations