INDEX

Explanations

phrases related to giving feedback or commentary

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating addition or continuation in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

idia

-0.74

retty

-0.68

Ãį

-0.67

 corrid

-0.64

stice

-0.64

ÑĮ

-0.59

isan

-0.59

ãĤ´ãĥ³

-0.59

ãĥĭ

-0.59

 dolphins

-0.59

POSITIVE LOGITS

eg

0.66

Wars

0.64

udeb

0.63

 namely

0.63

please

0.62

 Particularly

0.62

 Including

0.61

Koh

0.60

ie

0.59

 Spoiler

0.59

Activations Density 0.468%

phrases related to giving feedback or commentary

conjunctions and phrases indicating addition or continuation in sentences

No Comments

No Known Activations