© 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. 4210
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reporting

    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
    604
    +0.11
    0.3%
    1600
    +0.10
    0.3%
    382
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1430
    +0.11
    0.06
    1600
    +0.10
    0.06
    1162
    +0.07
    0.04
    Negative Logits
     tricot
    -0.73
     ampoule
    -0.73
     thermomix
    -0.72
     amigurumi
    -0.72
     softshell
    -0.71
     fusible
    -0.62
     hairc
    -0.62
     nori
    -0.60
     oleo
    -0.58
     CommandType
    -0.58
    POSITIVE LOGITS
     backlash
    0.65
     controversy
    0.64
     critics
    0.63
     reaksi
    0.61
     uproar
    0.60
    Reactions
    0.59
    Reaction
    0.58
     netizens
    0.58
     controver
    0.58
     outcry
    0.57
    Activations Density 0.724%

    No Known Activations