INDEX

Explanations

words related to tasks and instructions

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BooleanField

-0.53

twimg

-0.48

Mas

-0.47

ally

-0.45

ად

-0.43

 altında

-0.43

Mas

-0.42

 poil

-0.41

out

-0.40

 tilbage

-0.40

POSITIVE LOGITS

Vidite

0.93

 >=",

0.87

 utafitiHapana

0.86

AsUp

0.82

Bioaccumulative

0.80

NameInMap

0.77

)_/¯

0.73

EDEFAULT

0.73

]';

0.70

 Referential

0.69

Activations Density 0.346%

words related to tasks and instructions

No Comments

No Known Activations