Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13808
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or examples

    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
    1828
    +0.14
    0.4%
    1895
    +0.14
    0.4%
    1407
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1828
    +0.14
    0.06
    1895
    +0.14
    0.05
    1407
    +0.13
    0.05
    Negative Logits
     cabinet
    -0.52
     real
    -0.47
     Cabinet
    -0.47
    adə
    -0.46
    làm
    -0.45
     wanted
    -0.45
     нена
    -0.45
    Климат
    -0.45
     берегу
    -0.45
     bắp
    -0.45
    POSITIVE LOGITS
     ftu
    1.29
     fep
    1.27
     »>
    1.26
     fta
    1.25
     poff
    1.25
     fays
    1.23
     intersper
    1.23
     guarante
    1.23
     impra
    1.22
     vns
    1.21
    Activations Density 0.075%

    No Known Activations