INDEX

Explanations

phrases related to negative behavior and gossip in workplace settings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.74

 Autorisations

-0.67

principalTable

-0.65

 متعلقه

-0.61

 XCTest

-0.61

 ujednoznacz

-0.59

expandindo

-0.59

+#+#

-0.56

//});

-0.55

timewa

-0.54

POSITIVE LOGITS

 devant

1.42

 publicly

1.39

 أمام

1.35

 delante

1.29

 davanti

1.28

 public

1.20

 frente

1.13

public

1.06

 hadapan

1.04

 front

1.03

Activations Density 0.360%

phrases related to negative behavior and gossip in workplace settings

No Comments

No Known Activations