© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13909
    Prev
    Next
    INDEX
    Explanations

    sentences expressing shock, sadness, and sympathy towards victims of a tragic event

    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
    468
    +0.17
    0.5%
    604
    +0.10
    0.3%
    998
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.17
    0.08
    838
    +0.10
    0.05
    946
    +0.10
    0.06
    Negative Logits
     affez
    -1.07
     swarovski
    -1.03
     !...
    -1.01
     ecru
    -1.01
     broderie
    -0.99
     suscep
    -0.98
     gmbh
    -0.97
     ?...
    -0.95
     fluo
    -0.95
     bordeaux
    -0.93
    POSITIVE LOGITS
     incident
    1.00
     incidents
    0.83
     tragedy
    0.76
     occurrence
    0.75
     events
    0.70
     situation
    0.69
     happened
    0.68
     event
    0.68
    incident
    0.68
     tragic
    0.65
    Activations Density 0.522%

    No Known Activations