© 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. 10697
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the speaker is expressing their opinion or providing commentary

    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
    +0.08
    0.2%
    1581
    +0.08
    0.2%
    872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1598
    +0.08
    0.02
    814
    +0.08
    0.02
    1626
    +0.07
    0.02
    Negative Logits
      (
    -0.49
     désigne
    -0.49
     eorum
    -0.49
    ITÀ
    -0.47
     Ejercicio
    -0.47
    xw
    -0.46
     veu
    -0.45
     desg
    -0.44
     sappi
    -0.44
    Vaata
    -0.44
    POSITIVE LOGITS
     earlier
    0.78
    PerformLayout
    0.65
    earlier
    0.63
     above
    0.58
     faggot
    0.56
    CROSSTALK
    0.54
    awsze
    0.54
     EARL
    0.53
     afore
    0.53
     stickied
    0.53
    Activations Density 0.091%

    No Known Activations