© 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. 14151
    Prev
    Next
    INDEX
    Explanations

    statements related to capitalism and economic inequality

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    first-person statements and direct quotes.

    oai_token-act-pair · gpt-4oTriggered by @thinkspring96
    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
    100
    +0.11
    0.4%
    604
    +0.11
    0.3%
    1553
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.11
    0.11
    872
    +0.11
    0.15
    1380
    +0.10
    0.03
    Negative Logits
     fta
    -1.01
     magis
    -1.00
     aen
    -0.98
     ftu
    -0.97
     ?...
    -0.96
     !...
    -0.96
     fays
    -0.95
     ftre
    -0.95
     ··
    -0.94
     thut
    -0.93
    POSITIVE LOGITS
    rungsseite
    0.59
     reply
    0.50
     unacceptable
    0.48
    Bibliograf
    0.48
     sorry
    0.47
     inappropriate
    0.47
     response
    0.46
     snippetHide
    0.46
     anti
    0.45
     hate
    0.45
    Activations Density 3.787%

    No Known Activations