© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14695
    Prev
    Next
    INDEX
    Explanations

    phrases related to interpersonal relationships and dynamics

    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
    50
    +0.14
    0.4%
    736
    +0.13
    0.4%
    752
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.14
    0.09
    16
    +0.13
    0.09
    946
    +0.10
    0.07
    Negative Logits
    CRETE
    -0.76
    VISIONS
    -0.75
    bài
    -0.69
     mentales
    -0.67
    EMPT
    -0.63
     vueltas
    -0.63
    therosclerosis
    -0.62
     habitaciones
    -0.61
     imagenes
    -0.61
     laborales
    -0.61
    POSITIVE LOGITS
     accla
    1.19
     vagu
    1.14
     Abbé
    1.10
     calum
    1.10
     BIBSYS
    1.09
     sophistic
    1.08
     philanth
    1.08
     reluct
    1.08
     quoique
    1.08
     apprehen
    1.08
    Activations Density 0.785%

    No Known Activations