© 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 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. 5904
    Prev
    Next
    INDEX
    Explanations

    phrases related to denying or refuting allegations

    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
    453
    +0.07
    0.2%
    446
    +0.07
    0.2%
    1150
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1832
    +0.07
    0.03
    1285
    +0.07
    0.04
    1727
    +0.07
    0.03
    Negative Logits
     impra
    -1.36
     impractica
    -1.16
     bordeaux
    -1.14
     ecru
    -1.13
     tricot
    -1.12
     oleo
    -1.08
     unwarran
    -1.08
     swarovski
    -1.08
     nutella
    -1.05
     napoli
    -1.03
    POSITIVE LOGITS
     allegations
    1.03
     allegation
    0.89
     claims
    0.87
     accusations
    0.86
     claim
    0.81
     charges
    0.78
    claims
    0.75
     denies
    0.74
    Claims
    0.73
     deny
    0.72
    Activations Density 0.258%

    No Known Activations