© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7460
    Prev
    Next
    INDEX
    Explanations

    words related to education and careers

    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
    1531
    +0.10
    0.3%
    198
    +0.09
    0.3%
    994
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.10
    0.05
    51
    +0.09
    0.03
    1876
    +0.09
    0.04
    Negative Logits
     javier
    -1.47
     alberto
    -1.40
     jorge
    -1.37
     sergio
    -1.37
     roberto
    -1.36
     eduardo
    -1.31
     ricardo
    -1.23
     felipe
    -1.22
     lorenzo
    -1.16
     nicolas
    -1.15
    POSITIVE LOGITS
     everywhere
    1.11
     galore
    1.06
     apl
    0.81
    everywhere
    0.81
     ranging
    0.81
     every
    0.79
    ranging
    0.78
     throughout
    0.77
     EVERY
    0.70
    Everywhere
    0.69
    Activations Density 0.693%

    No Known Activations