© 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. 14340
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and actions

    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
    674
    +0.20
    0.6%
    897
    +0.11
    0.3%
    1334
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1351
    +0.20
    0.02
    1304
    +0.11
    0.02
    562
    +0.10
    0.02
    Negative Logits
     unlaw
    -0.98
     shenan
    -0.96
     disagre
    -0.94
     unwarran
    -0.94
     apprehen
    -0.91
     depic
    -0.91
     unspeak
    -0.90
     withal
    -0.88
     hairc
    -0.85
     maneu
    -0.84
    POSITIVE LOGITS
     anticipo
    0.56
     meras
    0.54
     algas
    0.54
     adoles
    0.53
     sfondo
    0.53
     perca
    0.52
     kosme
    0.52
    eclamp
    0.51
    <bos>
    0.51
     Foire
    0.50
    Activations Density 0.098%

    No Known Activations