© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12179
    Prev
    Next
    INDEX
    Explanations

    statements related to negotiations or responses in a context of discussions or disputes

    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
    674
    +0.16
    0.5%
    764
    +0.11
    0.3%
    1108
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    804
    +0.16
    0.04
    116
    +0.11
    0.03
    1081
    +0.09
    0.04
    Negative Logits
     increa
    -1.46
     impra
    -1.43
     hentai
    -1.39
     shenan
    -1.38
     encomp
    -1.38
     milf
    -1.36
     affor
    -1.35
     intersper
    -1.33
     excru
    -1.32
     inev
    -1.31
    POSITIVE LOGITS
     NSCoder
    0.68
     now
    0.67
    :+:
    0.66
    nodoc
    0.65
    ->___
    0.63
     архивлан
    0.61
    ChildScrollView
    0.60
     ahora
    0.60
    providedIn
    0.59
    Ahora
    0.58
    Activations Density 0.411%

    No Known Activations