© 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. 4717
    Prev
    Next
    INDEX
    Explanations

    positive experiences or events

    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
    1921
    +0.11
    0.3%
    553
    +0.10
    0.3%
    674
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.11
    0.06
    1856
    +0.10
    0.06
    658
    +0.10
    0.06
    Negative Logits
     maneu
    -1.27
     encomp
    -1.24
     reluct
    -1.23
     emphat
    -1.20
     depic
    -1.16
     increa
    -1.14
     affor
    -1.14
     strick
    -1.12
     effe
    -1.12
     snoopy
    -1.12
    POSITIVE LOGITS
    expandindo
    0.82
    AndEndTag
    0.76
     autorytatywna
    0.73
     bawat
    0.72
    BeginInit
    0.71
    PerformLayout
    0.71
    intios
    0.71
    醐
    0.69
     Drapeau
    0.68
     pagkak
    0.68
    Activations Density 0.330%

    No Known Activations