© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    adjectives related to weakness or vulnerability

    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
    347
    +0.17
    0.6%
    1350
    +0.14
    0.5%
    1677
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.17
    0.03
    1677
    +0.14
    0.02
    1350
    +0.13
    0.02
    Negative Logits
     finn
    -0.59
     gild
    -0.58
     zyn
    -0.58
     inder
    -0.58
     oner
    -0.58
     lts
    -0.58
     ?...
    -0.57
     Gies
    -0.57
     embra
    -0.57
     mme
    -0.56
    POSITIVE LOGITS
     weak
    1.25
    weak
    1.19
     Weak
    1.19
    Weak
    1.10
     weakest
    1.03
     weaker
    1.02
     weaken
    1.01
     weakness
    0.98
     weakened
    0.94
     weakening
    0.88
    Activations Density 0.065%

    No Known Activations