© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7435
    Prev
    Next
    INDEX
    Explanations

    phrases related to deception and dishonesty

    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
    122
    +0.12
    0.4%
    1557
    +0.10
    0.4%
    920
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1557
    +0.12
    0.02
    1983
    +0.10
    0.02
    122
    +0.10
    0.02
    Negative Logits
     karton
    -0.71
     kram
    -0.66
     krab
    -0.65
     klap
    -0.64
     keram
    -0.64
     meras
    -0.63
     republi
    -0.60
     malen
    -0.59
     eene
    -0.58
     moza
    -0.58
    POSITIVE LOGITS
     lie
    1.19
     lies
    1.10
     lying
    1.05
     lied
    1.04
     Lie
    1.04
    Lie
    0.99
     Lies
    0.97
     Lying
    0.94
     LIE
    0.89
    Lying
    0.87
    Activations Density 0.059%

    No Known Activations