© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14572
    Prev
    Next
    INDEX
    Explanations

    references to fictional or alternate worlds, specifically those that involve changes in historical events or societal structures

    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
    +0.21
    0.6%
    453
    +0.12
    0.4%
    1577
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.21
    0.05
    934
    +0.12
    0.02
    184
    +0.11
    0.01
    Negative Logits
     maneu
    -1.12
     scrat
    -1.04
     hairc
    -1.00
     indestru
    -0.98
     excru
    -0.96
     eyel
    -0.95
     peppa
    -0.94
     perfet
    -0.94
     encomp
    -0.94
     invin
    -0.93
    POSITIVE LOGITS
    商品説明
    0.79
    GEBURTSDATUM
    0.76
    EndInit
    0.69
    Espèce
    0.67
     desertcart
    0.67
    énario
    0.67
    AndEndTag
    0.60
    <bos>
    0.60
    CppMethod
    0.60
     kohdetta
    0.59
    Activations Density 0.422%

    No Known Activations