© 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. 4538
    Prev
    Next
    INDEX
    Explanations

    words related to confusion or misunderstanding

    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
    1533
    +0.10
    0.3%
    1438
    +0.09
    0.2%
    763
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1915
    +0.10
    0.04
    275
    +0.09
    0.03
    1533
    +0.08
    0.01
    Negative Logits
     excru
    -1.25
     reluct
    -1.23
     inconce
    -1.22
     impra
    -1.22
     guarante
    -1.21
     increa
    -1.20
     affor
    -1.17
     emphat
    -1.16
     maneu
    -1.14
     accla
    -1.14
    POSITIVE LOGITS
     actually
    0.62
     ternyata
    0.61
    WireFormatLite
    0.58
     really
    0.56
     hadn
    0.54
    原来
    0.53
     wasn
    0.52
    artifactId
    0.50
     weren
    0.50
    omorphisms
    0.50
    Activations Density 0.368%

    No Known Activations