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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4288
    Prev
    Next
    INDEX
    Explanations

    references to movie characters and actors

    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
    184
    +0.40
    1.7%
    1842
    +0.23
    1.0%
    198
    +0.21
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.40
    0.04
    1842
    +0.23
    0.04
    198
    +0.21
    0.04
    Negative Logits
    <bos>
    -0.80
    AutoScaleMode
    -0.66
    WindowConstants
    -0.64
     betweenstory
    -0.62
     Normdatei
    -0.56
    IVEREF
    -0.56
    Попис
    -0.55
     Wiktionnaire
    -0.53
    intios
    -0.48
    RegressionTest
    -0.48
    POSITIVE LOGITS
     saad
    0.51
     jaya
    0.51
     skimage
    0.49
    AddTagHelper
    0.49
     PLWABN
    0.48
     tuh
    0.48
     minValue
    0.47
    原始内容存档
    0.46
    förderung
    0.46
    ☺☺
    0.43
    Activations Density 0.286%

    No Known Activations