© 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. 5038
    Prev
    Next
    INDEX
    Explanations

    words related to specific projects or parts of a collective effort

    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
    1376
    +0.12
    0.4%
    131
    +0.11
    0.3%
    1671
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.12
    0.04
    1376
    +0.11
    0.04
    1983
    +0.10
    0.04
    Negative Logits
    inderella
    -0.51
    ouncil
    -0.51
     rowCount
    -0.50
     userEmail
    -0.49
     Krieges
    -0.49
     createDate
    -0.47
    leveland
    -0.47
     loggedIn
    -0.47
     esternos
    -0.46
    obbies
    -0.46
    POSITIVE LOGITS
    part
    1.07
     part
    1.04
    Part
    1.01
     Part
    0.96
     PART
    0.95
    PART
    0.81
    Parts
    0.76
     PARTS
    0.75
     Parts
    0.74
    parts
    0.73
    Activations Density 0.060%

    No Known Activations