INDEX

Explanations

phrases indicating questioning or seeking clarification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

tvguidetime

-0.66

ParallelGroup

-0.63

 ThemeData

-0.63

 bidra

-0.60

batore

-0.59

aarrggbb

-0.57

](#

-0.56

endpush

-0.55

جوايز

-0.54

ohio

-0.54

POSITIVE LOGITS

anema

0.54

 English

0.54

Cyfeiriadau

0.51

 foreigners

0.50

baran

0.50

 Foreign

0.49

english

0.49

webElementXpaths

0.48

EndGlobalSection

0.48

English

0.46

Activations Density 0.186%

phrases indicating questioning or seeking clarification

No Comments

No Known Activations