© 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. 3308
    Prev
    Next
    INDEX
    Explanations

    strong connections and contacts with experts and individuals involved in business activities

    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
    227
    +0.10
    0.3%
    1252
    +0.09
    0.3%
    143
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1252
    +0.10
    0.05
    143
    +0.09
    0.05
    198
    +0.09
    0.05
    Negative Logits
     effe
    -1.12
     thut
    -1.08
     igno
    -1.07
     emphat
    -1.06
     increa
    -1.03
     fup
    -1.00
     ftu
    -1.00
     disagre
    -0.99
     encomp
    -0.99
     inev
    -0.98
    POSITIVE LOGITS
     partnerships
    0.77
     partners
    0.72
     contacts
    0.67
    alitions
    0.65
     relationships
    0.62
     stakeholders
    0.60
     suppliers
    0.60
    assies
    0.59
     connections
    0.58
     sponsors
    0.58
    Activations Density 0.643%

    No Known Activations