INDEX

Explanations

terms related to legal and medical contexts, particularly focusing on concepts of good faith and fair dealing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 financière

-0.79

 neuve

-0.65

 dangereux

-0.63

 géographique

-0.62

 engraçadas

-0.60

katapos

-0.59

 sanguí

-0.58

 financeira

-0.58

béco

-0.57

 vacanze

-0.57

POSITIVE LOGITS

tive

0.98

sive

0.94

CodeAttribute

0.94

ative

0.91

IAL

0.82

atives

0.81

ATIVE

0.81

:✨

0.79

 Walkover

0.75

tives

0.72

Activations Density 2.757%

terms related to legal and medical contexts, particularly focusing on concepts of good faith and fair dealing

No Comments

No Known Activations