INDEX

Explanations

occurrences of the word "to" and its variations within the text

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

New Auto-Interp

Configuration

Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post

Features

65,536

Data Type

float32

Hook Name

blocks.25.hook_resid_post

Hook Layer

Architecture

gated

Context Size

1,024

Dataset

Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

reve

-0.15

EEK

-0.15

á»ĳt

-0.15

è¦ĭ

-0.14

pone

-0.14

jah

-0.14

ãģ«ãģĹãģ¦

-0.13

ormsg

-0.13

erts

-0.13

noch

-0.13

POSITIVE LOGITS

 whom

0.21

gether

0.21

 which

0.21

/from

0.21

 date

0.20

-date

0.19

wit

0.17

 support

0.17

 varying

0.17

 counter

0.17

Activations Density 0.342%

occurrences of the word "to" and its variations within the text

No Comments

No Known Activations