© 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. 13274
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with 'Well' for additional detail or a change in content

    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
    1265
    +0.14
    0.5%
    381
    +0.14
    0.4%
    872
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.14
    0.03
    1265
    +0.14
    0.03
    484
    +0.11
    0.02
    Negative Logits
    Hahahahaha
    -0.85
    Lma
    -0.78
    Noice
    -0.77
    Lmfao
    -0.74
     sappi
    -0.73
     lancia
    -0.67
    Ehh
    -0.67
    Hahah
    -0.66
     vogli
    -0.66
    Ikr
    -0.66
    POSITIVE LOGITS
     Well
    0.97
    Well
    0.93
     WELL
    0.88
    well
    0.86
     well
    0.85
     wells
    0.81
    WELL
    0.77
     Wells
    0.77
    wells
    0.66
    Wells
    0.64
    Activations Density 0.036%

    No Known Activations