© 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. 13779
    Prev
    Next
    INDEX
    Explanations

    phrases related to political ideologies and extremist groups

    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
    1870
    +0.12
    0.4%
    478
    +0.12
    0.4%
    678
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1624
    +0.12
    0.02
    678
    +0.12
    0.03
    757
    +0.12
    0.02
    Negative Logits
     And
    -0.60
    less
    -0.58
     Of
    -0.57
    <bos>
    -0.57
     No
    -0.57
     But
    -0.57
     At
    -0.56
     As
    -0.56
    BeforeAll
    -0.56
     My
    -0.56
    POSITIVE LOGITS
     effe
    1.62
     wien
    1.59
     increa
    1.53
     deleter
    1.51
     suspic
    1.50
     aen
    1.49
     sovere
    1.49
     nece
    1.49
     fatis
    1.49
     pessi
    1.48
    Activations Density 0.068%

    No Known Activations