INDEX

Explanations

the prefix "re-" in words, indicating repeated actions or iterations

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

prefix "re-" in words indicating repetition or going back to a previous state.

oai_token-act-pair · claude-3-5-haiku-20241022 Triggered by @neilrathi

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 myſelf

-1.42

 Majefty

-1.39

Efq

-1.30

 itſelf

-1.26

 pleaſure

-1.22

ſelf

-1.17

 ſeveral

-1.16

 Monfieur

-1.14

 ſever

-1.13

 perſon

-1.13

POSITIVE LOGITS

re

1.08

pro

1.02

po

0.84

pop

0.84

 trans

0.80

Mc

0.79

co

0.79

 inter

0.79

0.76

pop

0.75

Activations Density 0.171%

the prefix "re-" in words, indicating repeated actions or iterations

prefix "re-" in words indicating repetition or going back to a previous state.

No Comments

No Known Activations