Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3230
    Prev
    Next
    INDEX
    Explanations

    references to family and relationships, particularly highlighting feelings of love and understanding between family members

    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
    509
    +0.10
    0.3%
    1533
    +0.09
    0.3%
    227
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1543
    +0.10
    0.04
    1533
    +0.09
    0.02
    1081
    +0.09
    0.06
    Negative Logits
     thut
    -1.14
     dises
    -1.13
     fte
    -1.13
     lara
    -1.12
     aen
    -1.11
     fta
    -1.07
     daf
    -1.07
     roth
    -1.06
     „,
    -1.06
     mef
    -1.06
    POSITIVE LOGITS
    <bos>
    0.92
     love
    0.64
     loving
    0.60
     loves
    0.59
    Toujours
    0.57
     unconditional
    0.56
     cherish
    0.55
     affection
    0.54
     forever
    0.53
     Loving
    0.53
    Activations Density 0.521%

    No Known Activations