© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4924
    Prev
    Next
    INDEX
    Explanations

    descriptions of enthusiastic anticipation

    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
    674
    +0.39
    1.5%
    184
    +0.22
    0.9%
    1967
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.39
    0.01
    284
    +0.22
    0.03
    1992
    +0.13
    0.01
    Negative Logits
     maneu
    -1.05
     unspeak
    -1.04
     pamph
    -1.03
     embodi
    -1.03
     depic
    -1.03
     maer
    -1.00
     nephe
    -1.00
     indestru
    -1.00
     secon
    -0.99
     fluo
    -0.99
    POSITIVE LOGITS
    <bos>
    1.14
    ⓧ
    0.72
    <?
    0.71
    
    0.64
    Cependant
    0.62
    /**
    0.62
    🕗
    0.62
    <?
    0.60
     occupe
    0.60
     ressemble
    0.59
    Activations Density 0.255%

    No Known Activations