© 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. 2362
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflection and introspection

    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
    1350
    +0.09
    0.3%
    1416
    +0.09
    0.3%
    991
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1020
    +0.09
    0.03
    138
    +0.09
    0.03
    1652
    +0.09
    0.03
    Negative Logits
     inev
    -2.08
     increa
    -2.07
     squa
    -2.03
     fta
    -2.02
     reluct
    -2.02
     affor
    -2.01
     emphat
    -2.01
     disagre
    -2.00
     guarante
    -1.97
     fuf
    -1.95
    POSITIVE LOGITS
    <bos>
    1.31
     just
    0.70
    stylers
    0.67
     Просто
    0.67
    到
    0.63
     بن
    0.62
     be
    0.61
    换
    0.61
     weil
    0.61
    道
    0.61
    Activations Density 0.162%

    No Known Activations