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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14609
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversy and criticism

    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
    284
    +0.09
    0.3%
    344
    +0.09
    0.2%
    1662
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.09
    0.09
    1662
    +0.09
    0.07
    1553
    +0.08
    0.07
    Negative Logits
     aen
    -0.94
     thut
    -0.82
     fta
    -0.80
     »>
    -0.80
     intersper
    -0.80
     juf
    -0.79
     ftu
    -0.78
     kani
    -0.78
     hcm
    -0.77
     javier
    -0.76
    POSITIVE LOGITS
     via
    0.63
     by
    0.63
     while
    0.62
     through
    0.60
    TargetException
    0.57
    while
    0.55
     whilst
    0.53
     indem
    0.52
     unnecessarily
    0.52
     bằng
    0.51
    Activations Density 0.665%

    No Known Activations