INDEX

Explanations

phrases containing the word "said"

oai_token-act-pair · gpt-3.5-turbo

instances of reporting or quoting information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ajo

-0.93

anu

-0.75

ments

-0.70

ental

-0.68

otin

-0.65

 renters

-0.64

imar

-0.63

ription

-0.62

atton

-0.62

MENT

-0.61

POSITIVE LOGITS

ãĥ¼ãĥĨ

0.79

è¦ļéĨĴ

0.76

 âĨĳ

0.66

Override

0.65

ĳå£«

0.65

 Incarn

0.64

escription

0.63

ynamic

0.62

 incidentally

0.62

 Topic

0.62

Activations Density 0.101%

phrases containing the word "said"

instances of reporting or quoting information

No Comments

No Known Activations