INDEX

Explanations

structured sentences that present facts, warnings, or errors, often with an emphasis on important details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

↵↵

-0.63

 المعيارى

-0.55

MigrationBuilder

-0.54

 bezeichneter

-0.52

↵↵↵

-0.44

↵

-0.44

ValueStyle

-0.43

ことも

-0.43

 besonderes

-0.42

ırlı

-0.42

POSITIVE LOGITS

CPtr

0.86

 pinulongan

0.85

 BoxFit

0.78

 ujednoznacz

0.77

principalColumn

0.76

CppCodeGen

0.73

UnitTesting

0.72

 ItemStack

0.70

SizeMode

0.70

denly

0.69

Activations Density 0.300%

structured sentences that present facts, warnings, or errors, often with an emphasis on important details

No Comments

No Known Activations