INDEX

Explanations

phrases related to sequential actions or events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "when" to indicate temporal context

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

ãĥ³ãĤ¸

-0.63

º

-0.62

İ

-0.62

Ī

-0.62

ãĤ´ãĥ³

-0.61

¬¼

-0.60

ailing

-0.59

 workaround

-0.58

²¾

-0.58

¹

-0.58

POSITIVE LOGITS

 however

0.72

 Brav

0.65

 Ambro

0.65

 namely

0.64

dos

0.62

 THEN

0.62

aka

0.59

 beware

0.57

enko

0.57

 Skydragon

0.57

Activations Density 0.292%

phrases related to sequential actions or events

instances of the word "when" to indicate temporal context

No Comments

No Known Activations