© 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. 14176
    Prev
    Next
    INDEX
    Explanations

    terms related to the White House

    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
    1741
    +0.11
    0.4%
    1127
    +0.10
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1127
    +0.11
    0.02
    1178
    +0.10
    0.03
    208
    +0.10
    0.03
    Negative Logits
     affor
    -1.51
     increa
    -1.49
     swarovski
    -1.49
     perfet
    -1.48
     peppa
    -1.46
     inev
    -1.46
     encomp
    -1.43
     reluct
    -1.43
     impra
    -1.40
     unden
    -1.40
    POSITIVE LOGITS
     House
    0.90
    House
    0.81
     house
    0.74
    house
    0.73
     presidential
    0.66
    HOUSE
    0.66
    RTSC
    0.66
    exitRule
    0.65
     Office
    0.64
    ESOME
    0.63
    Activations Density 0.073%

    No Known Activations