INDEX

Explanations

instances of connecting words, particularly conjunctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ſelf

-1.17

 itſelf

-1.15

 ―――――

-1.07

 ་་

-1.06

 ſind

-1.05

 iſt

-0.99

 raiſ

-0.97

 ſtate

-0.97

 uſed

-0.96

ſelves

-0.96

POSITIVE LOGITS

1.19

you

1.02

it

0.95

we

0.88

0.79

if

0.78

my

0.77

 they

0.76

..

0.76

 alot

0.75

Activations Density 0.289%

instances of connecting words, particularly conjunctions

No Comments

No Known Activations