INDEX

Explanations

phrases indicating conditions or exceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

})`

-0.56

уда

-0.52

stwie

-0.51

 userDao

-0.50

 pict

-0.50

Più

-0.50

 laiko

-0.50

 ſtate

-0.50

 bacio

-0.50

 interesan

-0.50

POSITIVE LOGITS

MessageTagHelper

0.72

 ведь

0.70

Ведь

0.69

 totiž

0.68

 przecież

0.64

 bowiem

0.61



0.60

 '\\;'

0.57

 kasarigan

0.57

 فهي

0.57

Activations Density 0.101%

phrases indicating conditions or exceptions

No Comments

No Known Activations