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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14934
    Prev
    Next
    INDEX
    Explanations

    negative sentiments or refusals

    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
    1757
    +0.14
    0.5%
    411
    +0.14
    0.4%
    674
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    411
    +0.14
    0.06
    581
    +0.14
    0.06
    1622
    +0.11
    0.04
    Negative Logits
     soigne
    -0.96
     habile
    -0.94
     Chapitre
    -0.94
     épu
    -0.90
     Intere
    -0.85
     Simult
    -0.85
     Confu
    -0.85
     hcm
    -0.84
     triomphe
    -0.84
     désol
    -0.83
    POSITIVE LOGITS
     autorytatywna
    0.82
    <bos>
    0.69
     wont
    0.66
     be
    0.64
    Cyfeiriadau
    0.63
     necessarily
    0.62
     intptr
    0.62
     won
    0.62
     disambiguazione
    0.60
    Personensuche
    0.59
    Activations Density 0.159%

    No Known Activations