© 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. 15233
    Prev
    Next
    INDEX
    Explanations

    timestamps

    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
    59
    +0.07
    0.2%
    309
    +0.07
    0.2%
    1398
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1433
    +0.07
    0.05
    99
    +0.07
    0.04
    309
    +0.07
    0.05
    Negative Logits
    ThroughAttribute
    -0.64
     defaultstate
    -0.64
    Kaip
    -0.61
     nakalista
    -0.61
    原始内容
    -0.60
    Asimismo
    -0.58
    richTextPanel
    -0.58
    styleType
    -0.57
    Pautan
    -0.56
    Nasc
    -0.56
    POSITIVE LOGITS
     impra
    1.47
     maneu
    1.43
     reluct
    1.36
     shenan
    1.33
     disreg
    1.31
     intersper
    1.29
     attemp
    1.28
     depic
    1.28
     strick
    1.27
     resear
    1.26
    Activations Density 0.256%

    No Known Activations