© 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. 13373
    Prev
    Next
    INDEX
    Explanations

    that span multiple words related to career and personal development

    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
    74
    +0.08
    0.2%
    58
    +0.08
    0.2%
    369
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.08
    0.03
    1718
    +0.08
    0.05
    875
    +0.07
    0.03
    Negative Logits
     increa
    -0.84
     scrat
    -0.84
     reluct
    -0.81
     guarante
    -0.80
     effe
    -0.78
     unden
    -0.78
    YMMV
    -0.77
     perfet
    -0.76
     purcha
    -0.76
     encomp
    -0.76
    POSITIVE LOGITS
     lost
    0.98
    lost
    0.86
    Lost
    0.71
     Lost
    0.69
     regained
    0.68
     restored
    0.68
     forgotten
    0.67
     LOST
    0.65
     stolen
    0.65
     damaged
    0.64
    Activations Density 0.342%

    No Known Activations