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. 390
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and legal proceedings

    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
    453
    +0.10
    0.3%
    946
    +0.10
    0.3%
    184
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.10
    0.06
    167
    +0.10
    0.03
    1957
    +0.08
    0.03
    Negative Logits
     menthe
    -0.64
     matel
    -0.63
     herbes
    -0.62
     cioc
    -0.60
     laine
    -0.58
     poire
    -0.58
     bicic
    -0.58
     persil
    -0.57
     asfalto
    -0.57
     frambo
    -0.56
    POSITIVE LOGITS
     réaliste
    0.76
     exceptionnelle
    0.68
     régulier
    0.68
    XmlEnum
    0.67
    Quiénes
    0.66
    /**
    0.66
    Referencie
    0.63
    Glej
    0.61
    ⓧ
    0.61
     shewn
    0.60
    Activations Density 0.274%

    No Known Activations