© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or actions of individuals

    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
    184
    +0.20
    0.6%
    1842
    +0.19
    0.6%
    674
    +0.18
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.20
    0.03
    605
    +0.19
    0.01
    1419
    +0.18
    0.04
    Negative Logits
     depic
    -1.15
     encomp
    -1.12
     inev
    -1.10
     disagre
    -1.09
     apprehen
    -1.05
     „,
    -1.05
     increa
    -1.04
     Juf
    -1.04
     hcm
    -1.04
     alre
    -1.03
    POSITIVE LOGITS
     himself
    1.31
     his
    1.12
    himself
    1.08
     Himself
    0.90
    his
    0.90
     he
    0.75
    His
    0.74
     His
    0.72
     seiner
    0.72
     seinem
    0.70
    Activations Density 0.543%

    No Known Activations