INDEX

Explanations

terms related to the prefix "un-" indicating negation or reversal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 wireType

-0.95

 ainfi

-0.92

 MainAxisSize

-0.90

 SAGE

-0.88

 gynhyrchwyd

-0.87

 auffi

-0.86

 myſelf

-0.85

 itſelf

-0.85

 Phry

-0.84

 protoimpl

-0.83

POSITIVE LOGITS

UN

1.26

un

1.22

Un

1.19

UN

1.16

un

1.08

Un

1.04

Bun

1.04

Dun

0.99

0.97

bun

0.95

Activations Density 0.144%

terms related to the prefix "un-" indicating negation or reversal

No Comments

No Known Activations