INDEX

Explanations

terms related to usage and application contexts

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

 propOrder

-0.91

ConstraintMaker

-0.78

:✨

-0.72

IUrlHelper

-0.70

styleType

-0.66

BeginInit

-0.66

 reç

-0.65

ValueStyle

-0.65

 Roskov

-0.64

 bezeichneter

-0.64

POSITIVE LOGITS

 Used

0.83

 used

0.83

Used

0.72

for

0.69

 USED

0.69

 help

0.67

 用于

0.64

用于

0.63

用来

0.62

ToUse

0.62

Activations Density 0.344%

terms related to usage and application contexts

No Comments

No Known Activations