Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14070
    Prev
    Next
    INDEX
    Explanations

    information related to natural disasters and governmental responses

    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
    939
    +0.11
    0.3%
    1652
    +0.11
    0.3%
    468
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.11
    0.06
    1652
    +0.11
    0.04
    1499
    +0.10
    0.05
    Negative Logits
     spie
    -0.62
    AMILTON
    -0.55
     applau
    -0.53
     :)))
    -0.53
    Activité
    -0.52
    uggest
    -0.52
    Activités
    -0.51
     gambe
    -0.51
     Respiration
    -0.51
    FetchType
    -0.50
    POSITIVE LOGITS
     devastation
    0.59
     devastated
    0.59
     disaster
    0.55
     floods
    0.53
     devastating
    0.52
     ravaged
    0.49
     flooding
    0.48
     catastrophic
    0.47
     disasters
    0.47
     hurricane
    0.47
    Activations Density 0.385%

    No Known Activations