INDEX

Explanations

words related to colors and descriptions of objects

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

СТВА

-0.76

setContentView

-0.76

ึ้น

-0.68

ОВО

-0.68

-0.65

 down

-0.64

al

-0.63

downe

-0.62

 idea

-0.61

POSITIVE LOGITS

 незавершена

1.13

]='\

1.02

Билгалдахарш

0.97

 ſind

0.93

]--;

0.77

 ujednoznacz

0.77

 Houſe

0.76

ніципалі

0.75

 Reſ

0.73

 Inſ

0.73

Activations Density 0.023%

words related to colors and descriptions of objects

No Comments

No Known Activations