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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 455
    Prev
    Next
    INDEX
    Explanations

    references to specific gaming consoles such as Xbox One and PlayStation

    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
    1741
    +0.14
    0.5%
    687
    +0.14
    0.5%
    1984
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1352
    +0.14
    0.02
    687
    +0.14
    0.02
    1798
    +0.10
    0.02
    Negative Logits
    HtmlAttribute
    -0.66
    Bardzo
    -0.60
    Może
    -0.57
    Więcej
    -0.56
    Dlaczego
    -0.55
    Då
    -0.54
    DebuggerStep
    -0.53
    película
    -0.52
    typeDefinition
    -0.52
    Mejores
    -0.51
    POSITIVE LOGITS
    Xbox
    1.15
     Xbox
    1.11
     xbox
    1.00
    xbox
    0.88
     dinosau
    0.78
     predecess
    0.78
     flé
    0.74
     tén
    0.74
     Gouver
    0.72
     italia
    0.71
    Activations Density 0.051%

    No Known Activations