© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12654
    Prev
    Next
    INDEX
    Explanations

    monetary values in foreign currency

    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
    1343
    +0.10
    0.3%
    176
    +0.07
    0.2%
    1966
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.10
    0.03
    1343
    +0.07
    0.03
    1241
    +0.07
    0.02
    Negative Logits
     encomp
    -2.30
     intersper
    -2.27
     increa
    -2.25
     fta
    -2.22
     reluct
    -2.20
     maneu
    -2.19
     impra
    -2.19
     strick
    -2.16
     guarante
    -2.14
     fortn
    -2.13
    POSITIVE LOGITS
     nonatomic
    0.68
    IsContent
    0.67
    ActionCreators
    0.65
    ]-\
    0.64
    HtmlAttribute
    0.64
    Chất
    0.62
    modb
    0.61
    mtd
    0.61
    Források
    0.60
    PageRoute
    0.60
    Activations Density 0.067%

    No Known Activations