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. 15553
    Prev
    Next
    INDEX
    Explanations

    phrases related to unusual, shocking, or disturbing behavior

    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
    1935
    +0.08
    0.2%
    742
    +0.08
    0.2%
    1553
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.08
    0.07
    1553
    +0.08
    0.06
    1935
    +0.07
    0.04
    Negative Logits
     „,
    -1.17
     saar
    -1.16
     meis
    -1.16
     Teks
    -1.14
     Minang
    -1.13
     franz
    -1.10
     hina
    -1.08
     siff
    -1.07
     uhr
    -1.05
     liev
    -1.05
    POSITIVE LOGITS
     kepada
    0.84
     to
    0.73
     onto
    0.69
     unto
    0.68
     via
    0.67
     into
    0.62
     through
    0.61
     إلى
    0.59
     către
    0.58
     towards
    0.56
    Activations Density 0.461%

    No Known Activations