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. 2847
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy or conflict, particularly around online harassment

    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
    2034
    +0.23
    0.7%
    382
    +0.15
    0.5%
    1535
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.23
    0.10
    1535
    +0.15
    0.07
    1200
    +0.15
    0.07
    Negative Logits
     hairc
    -1.37
     fuf
    -1.36
     scrat
    -1.30
     increa
    -1.28
     sappi
    -1.27
     guarante
    -1.27
     chrysler
    -1.25
     emphat
    -1.24
     unve
    -1.24
     maneu
    -1.23
    POSITIVE LOGITS
     Instead
    0.85
     They
    0.84
     Specifically
    0.75
     ***!
    0.74
     Firstly
    0.71
    They
    0.70
     He
    0.70
     After
    0.69
    ])):
    0.69
    Instead
    0.69
    Activations Density 0.596%

    No Known Activations