© 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. 4038
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences, storytelling, and emotional reflections

    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
    80
    +0.10
    0.3%
    652
    +0.09
    0.3%
    1373
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1809
    +0.10
    0.04
    809
    +0.09
    0.05
    652
    +0.09
    0.05
    Negative Logits
     tyn
    -1.10
     guarante
    -1.09
     naer
    -1.08
     karton
    -1.08
     stik
    -1.08
     tille
    -1.06
     affor
    -1.06
     saar
    -1.05
     silikon
    -1.04
     encomp
    -1.03
    POSITIVE LOGITS
     struggles
    0.75
     experiences
    0.69
     journey
    0.68
     adventures
    0.66
     struggle
    0.65
     lives
    0.62
     how
    0.62
     events
    0.62
     journeys
    0.61
     fascinating
    0.60
    Activations Density 0.538%

    No Known Activations