© 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. 2100
    Prev
    Next
    INDEX
    Explanations

    negotiation and business terms

    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
    604
    +0.14
    0.4%
    674
    +0.10
    0.3%
    1042
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    915
    +0.14
    0.04
    959
    +0.10
    0.04
    330
    +0.10
    0.03
    Negative Logits
     emphat
    -1.51
     disagre
    -1.38
     increa
    -1.30
     encomp
    -1.28
     accla
    -1.27
     apprehen
    -1.26
     ftu
    -1.26
     shenan
    -1.25
     contribut
    -1.25
     uninten
    -1.23
    POSITIVE LOGITS
    unlikely
    0.74
     unlikely
    0.74
     likely
    0.69
    likely
    0.59
     difficult
    0.57
     likelihood
    0.56
     unless
    0.55
     NSCoder
    0.54
    ftagPool
    0.53
     يتيمه
    0.53
    Activations Density 0.525%

    No Known Activations