© 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. 14567
    Prev
    Next
    INDEX
    Explanations

    details about close relationships, bonds, and emotional connections between individuals

    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
    1533
    +0.09
    0.3%
    74
    +0.09
    0.3%
    1252
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    74
    +0.09
    0.03
    1287
    +0.09
    0.03
    1580
    +0.08
    0.04
    Negative Logits
     hcm
    -1.24
     aen
    -1.18
     daf
    -1.17
     mef
    -1.13
     inev
    -1.13
     dises
    -1.13
     ivi
    -1.11
     §.
    -1.11
     reluct
    -1.10
     effe
    -1.10
    POSITIVE LOGITS
     relationship
    0.88
     relationships
    0.85
     friendship
    0.81
    relationship
    0.77
     Relationship
    0.74
     friendships
    0.73
    relationships
    0.70
     bond
    0.69
     bonds
    0.66
    Relationship
    0.65
    Activations Density 0.404%

    No Known Activations