Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2619
    Prev
    Next
    INDEX
    Explanations

    movie titles transformed into comical parodies with the replacement of characters by celebrities along with event information

    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
    227
    +0.19
    0.6%
    1343
    +0.15
    0.5%
    1150
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.19
    0.04
    981
    +0.15
    0.04
    1343
    +0.14
    0.03
    Negative Logits
    Autoritní
    -0.86
     مرئيه
    -0.85
    Personendaten
    -0.83
    tagHelperRunner
    -0.82
     Roskov
    -0.80
     fundas
    -0.77
     lapto
    -0.75
    AsUp
    -0.75
    Ưu
    -0.75
     Paglinawan
    -0.74
    POSITIVE LOGITS
     depic
    1.51
     snoopy
    1.37
     hentai
    1.29
     indestru
    1.29
     inappro
    1.28
     uniqu
    1.28
     strick
    1.25
     attemp
    1.25
     impra
    1.24
     maneu
    1.24
    Activations Density 0.105%

    No Known Activations