INDEX

Explanations

phrases that indicate causes or reasons for actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

isseurs

-0.50

addPreferredGap

-0.47

 pector

-0.47

 дописавши

-0.46

 Alembic

-0.44

CppMethod

-0.44

 copil

-0.44

addComponent

-0.44

 fornic

-0.43

corner

-0.43

POSITIVE LOGITS

GraphicsUnit

0.69

 Roskov

0.69

ValueGenerated

0.68

 occasional

0.64

Personendaten

0.63

 发表于

0.63

tration

0.62

FunctionFlags

0.62

 slight

0.61

Rüyada

0.61

Activations Density 0.210%

phrases that indicate causes or reasons for actions or states

No Comments

No Known Activations