INDEX

Explanations

terms related to legal classifications and definitions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ariatric

-0.54

principalTable

-0.53

 Theſe

-0.50

yab

-0.49

gart

-0.47

 Pingback

-0.47

fromnode

-0.46

 Capsules

-0.45

BibitemShut

-0.45

אות

-0.45

POSITIVE LOGITS

 lenker

0.83

 createSlice

0.81

 فريبيس

0.65

CodeAttribute

0.62

ležit

0.57

walde

0.54

MeasureSpec

0.54

يميديا

0.53

 estrictamente

0.52

 presenza

0.51

Activations Density 0.765%

terms related to legal classifications and definitions

No Comments

No Known Activations