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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1586
    Prev
    Next
    INDEX
    Explanations

    phrases containing advice on managing emotions and relationships

    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
    478
    +0.11
    0.3%
    1510
    +0.08
    0.2%
    1097
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.11
    0.03
    646
    +0.08
    0.04
    1209
    +0.07
    0.04
    Negative Logits
     fup
    -1.10
     fte
    -1.09
     ftu
    -1.05
     fta
    -1.05
     fep
    -1.03
     fei
    -1.02
     secon
    -1.02
     hcm
    -1.01
     frankfurt
    -1.00
     squa
    -0.98
    POSITIVE LOGITS
     success
    0.66
     better
    0.63
     happier
    0.62
     succeed
    0.61
     easier
    0.58
    success
    0.57
     successful
    0.55
     successes
    0.55
     successfully
    0.53
    jws
    0.53
    Activations Density 0.386%

    No Known Activations