INDEX

Explanations

legal terminology related to liability and disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 sometimes

-0.61

Sometimes

-0.57

 Sometimes

-0.55

 possibly

-0.49

 maybe

-0.48

Surely

-0.47

<sup>

-0.47

 usually

-0.46

 occasionally

-0.45

 mostly

-0.45

POSITIVE LOGITS

findpost

1.11

 Мексичка

1.10

Personensuche

1.02

 '\\;'

0.99

webElement

0.98

IntoConstraints

0.98

 فريبيس

0.98

 NSCoder

0.98



0.95

BufferException

0.94

Activations Density 0.317%

legal terminology related to liability and disclaimers

No Comments

No Known Activations