INDEX

Explanations

references to travel or trips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

unton

-0.63

солю

-0.59

bParam

-0.56

djangoproject

-0.53

 ſmall

-0.53

IZONT

-0.53

,:]

-0.51

||}

-0.50

/>\

-0.50

 معت

-0.50

POSITIVE LOGITS

tych

0.72

 into

0.70

 naar

0.65

 során

0.63

 undertaken

0.60

Tikang

0.60



0.58

Into

0.57

advisor

0.57

trip

0.56

Activations Density 0.136%

references to travel or trips

No Comments

No Known Activations