INDEX

Explanations

terms related to authority and power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ProgressHUD

-0.55

-0.52

 referrerpolicy

-0.51

-0.47

urem

-0.45

orElseThrow

-0.45

ma

-0.44

Allowance

-0.44

ge

-0.44

skor

-0.44

POSITIVE LOGITS

 myſelf

0.87

Démographie

0.78

 nevoie

0.78

 EconPapers

0.76

rungsseite

0.75

 mijne

0.74

IsContent

0.71

 feminina

0.69

 itſelf

0.68

__':

0.68

Activations Density 1.243%

terms related to authority and power dynamics

No Comments

No Known Activations