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

    Neuronpedia

    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. 13231
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace organization and time management

    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
    1252
    +0.09
    0.2%
    963
    +0.08
    0.2%
    1129
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    963
    +0.09
    0.05
    1290
    +0.08
    0.06
    1428
    +0.08
    0.02
    Negative Logits
     wherea
    -1.20
     increa
    -1.16
     fortn
    -1.16
     volunte
    -1.16
     reluct
    -1.15
     squa
    -1.13
     accla
    -1.12
     disagre
    -1.12
     depic
    -1.12
     secon
    -1.10
    POSITIVE LOGITS
     convincing
    0.84
     persuade
    0.84
     convince
    0.83
     persuasive
    0.76
     persuasion
    0.71
    vincing
    0.68
     appeal
    0.64
     thuyết
    0.64
    transQ
    0.63
     persuading
    0.62
    Activations Density 0.644%

    No Known Activations