INDEX

Explanations

the word "set" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 tear

-0.59

 '\\;'

-0.54

िक्ष

-0.53

 cast

-0.52

ارو

-0.51

 completely

-0.51

 part

-0.50

heartedly

-0.49

co

-0.48

vorg

-0.48

POSITIVE LOGITS

SET

1.09

MemoryWarning

0.91

SET

0.77

 nucléaire

0.75

endphp

0.75

(!__

0.75

Set

0.74

 inoxydable

0.73

 mourut

0.73

0.70

Activations Density 0.115%

the word "set" and its variations in different contexts

No Comments

No Known Activations