© 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. 7777
    Prev
    Next
    INDEX
    Explanations

    phrases related to online harassment or abuse

    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
    1842
    +0.33
    1.1%
    1343
    +0.21
    0.7%
    1967
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.33
    0.06
    1801
    +0.21
    0.04
    1129
    +0.20
    0.08
    Negative Logits
    THEOREM
    -0.57
    Manbalar
    -0.56
     autorytatywna
    -0.54
    Denote
    -0.53
     vectorial
    -0.52
    Corollary
    -0.50
    Glej
    -0.47
     vry
    -0.46
     $-.
    -0.46
    Demografía
    -0.45
    POSITIVE LOGITS
     enrique
    0.54
     =>'
    0.48
     recueil
    0.48
    Xoxo
    0.48
    lllllllll
    0.47
     actualité
    0.45
     eduardo
    0.45
     Chapitre
    0.43
     curé
    0.43
     vestiti
    0.43
    Activations Density 0.852%

    No Known Activations