© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal characteristics, beliefs, and thoughts

    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
    1446
    +0.10
    0.3%
    1343
    +0.08
    0.2%
    2006
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2030
    +0.10
    0.03
    1135
    +0.08
    0.03
    533
    +0.08
    0.05
    Negative Logits
     maksi
    -0.91
     protokol
    -0.81
     optik
    -0.81
     seksi
    -0.80
     keramik
    -0.78
     saar
    -0.76
     panik
    -0.75
     kön
    -0.74
     ekos
    -0.73
     praktik
    -0.73
    POSITIVE LOGITS
     willingness
    0.82
     pymysql
    0.81
     heapq
    0.75
     desire
    0.73
     hashlib
    0.68
     declarat
    0.68
     boîtes
    0.66
     belief
    0.66
     tendency
    0.65
     sense
    0.65
    Activations Density 0.390%

    No Known Activations