INDEX

Explanations

variations of the word "straight."

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

Portale

-1.25

#+#

-1.18

PhysRevD

-1.05

complexContent

-0.96

Demografia

-0.96

JNIEnv

-0.93

RepeatedField

-0.93

Personensuche

-0.93

SceneManagement

-0.93

 Lordships

-0.92

POSITIVE LOGITS

 straight

1.62

 Straight

1.52

straight

1.51

Straight

1.48

 STRA

1.22

直

1.04

 straightforward

0.90

 strait

0.84

right

0.81

直

0.80

Activations Density 0.041%

variations of the word "straight."

No Comments

No Known Activations