INDEX

Explanations

keywords related to expressions of warranty or legal disclaimers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 cellpadding

-0.70

Aar

-0.60

omon

-0.59

Aar

-0.57

 Jolla

-0.55

ędzy

-0.55

 Mathieu

-0.54

henge

-0.54

 lucre

-0.54

tamen

-0.53

POSITIVE LOGITS

 Express

3.33

Express

3.28

 express

3.11

express

3.10

 EXPRESS

3.09

EXPRESS

2.61

 expresses

2.21

 expressing

1.98

 expressed

1.97

xpress

1.79

Activations Density 0.060%

keywords related to expressions of warranty or legal disclaimers

No Comments

No Known Activations