INDEX

Explanations

code-related elements and structures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

principalTable

-1.17

 الحره

-0.88

 للاسماء

-0.81

 ujednoznacz

-0.75

EDEFAULT

-0.70

 transfieras

-0.69

__":

-0.69

出版年

-0.68

 تضيفلها

-0.68

__':

-0.66

POSITIVE LOGITS

tedly

0.51

PutMapping

0.49

 Heine

0.43

velte

0.40

LinkId

0.39

BNF

0.39

GeneratedValue

0.38

zzleHttp

0.37

념

0.37

Mod

0.36

Activations Density 0.037%

code-related elements and structures

No Comments

No Known Activations