© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13301
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues and accusations of wrongdoing

    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
    1499
    +0.09
    0.2%
    1150
    +0.08
    0.2%
    1097
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1621
    +0.09
    0.04
    734
    +0.08
    0.04
    1997
    +0.08
    0.04
    Negative Logits
     swarovski
    -0.96
     ecru
    -0.83
     nutella
    -0.72
     tupperware
    -0.66
     paisley
    -0.58
     glycerin
    -0.58
     mascarpone
    -0.57
     getSize
    -0.56
     burlap
    -0.56
     oreo
    -0.56
    POSITIVE LOGITS
     said
    0.69
     says
    0.68
    says
    0.64
    said
    0.62
    &
    0.60
     alleges
    0.59
     dovrebbero
    0.58
     todav
    0.58
     abbiano
    0.57
     affatto
    0.57
    Activations Density 0.189%

    No Known Activations