INDEX

Explanations

programming-related keywords and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 tartalomajánló

-0.85

RectangleBorder

-0.82

 myſelf

-0.74

 виправивши

-0.72

 Theſe

-0.72

 Jefus

-0.72

 whoſe

-0.71

`{.

-0.70

 Anſ

-0.69

GEBURTSDATUM

-0.69

POSITIVE LOGITS

ří

0.46

ﾟ)

0.44

遂

0.44

int

0.43

contentLoaded

0.43

 based

0.43

座

0.42

PROTOBUF

0.41

 intern

0.41

int

0.41

Activations Density 0.858%

programming-related keywords and syntax

No Comments

No Known Activations