INDEX

Explanations

questions about past events or circumstances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 ſta

-0.84

 itſelf

-0.83

Efq

-0.82

 myſelf

-0.81

 Therefore

-0.80

TagHelper

-0.80

 ſtate

-0.79

ſelf

-0.78

 ſeveral

-0.77

Therefore

-0.77

POSITIVE LOGITS

Was

1.17

Was

1.13

was

1.06

WAS

0.96

WAS

0.89

water

0.70

 wasted

0.59

YouTube

0.54

 Wash

0.53

waters

0.53

Activations Density 0.040%

questions about past events or circumstances

No Comments

No Known Activations