INDEX

Explanations

references to geographical or structural features in descriptions

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

after "the" or "for"

np_acts-logits-general · gemini-2.0-flash

"for" context clues

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.56

 Specifically

-0.54

 specifically

-0.54

Specifically

-0.51

 substantially

-0.50

 professional

-0.50

 related

-0.50

 involves

-0.49

ditionally

-0.47

POSITIVE LOGITS

tagext

0.92

writeFieldEnd

0.84

 lazily

0.80

Tikang

0.80

__":

0.80

ientôt

0.77

 utafitiHapana

0.76

 glistening

0.76

ypeł

0.75

SharedDtor

0.74

Activations Density 0.266%

references to geographical or structural features in descriptions

after "the" or "for"

"for" context clues

No Comments

No Known Activations