INDEX

Explanations

code snippets that involve data processing and error handling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 brought

-0.51

The

-0.51

-0.49

 These

-0.49

far

-0.48

‘

-0.47

 support

-0.45

-0.44

end

-0.43

 para

-0.43

POSITIVE LOGITS



0.91

principalColumn

0.91

yntaxException

0.83

ArgsConstructor

0.81

 MainAxisSize

0.80

 Paglinawan

0.79

QMetaType

0.78

 propOrder

0.75

 الاطلاع

0.74

Handlung

0.73

Activations Density 0.178%

code snippets that involve data processing and error handling

No Comments

No Known Activations