INDEX

Explanations

terms related to resignations and firings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 piaci

-0.55

amitié

-0.52

 Réponses

-0.51

Filip

-0.48

 مُعرِّف

-0.47

quel

-0.47

Locking

-0.47

Eph

-0.46

zusch

-0.46

 Filip

-0.46

POSITIVE LOGITS

 démission

0.88

/*

0.78

 quitting

0.78

 quitted

0.75

 resignation

0.74

 quits

0.71

BeginContext

0.71

 resigned

0.69

 quit

0.69

 resigning

0.68

Activations Density 0.373%

terms related to resignations and firings

No Comments

No Known Activations