INDEX

Explanations

verbs indicating communication, intention, and assertion

oai_token-act-pair · gpt-3.5-turbo

phrases that denote indication, suggestion, or signaling information

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

ctors

-0.86

fare

-0.85

@#&

-0.80

zanne

-0.72

ÄŁ

-0.71

sites

-0.70

neys

-0.70

ney

-0.68

ps

-0.67

vas

-0.67

POSITIVE LOGITS

 indications

0.90

 signs

0.89

ered

0.83

 indication

0.79

 Signs

0.77

ively

0.72

 otherwise

0.72

 indicated

0.72

 indicates

0.71

 hints

0.71

Activations Density 0.038%

verbs indicating communication, intention, and assertion

phrases that denote indication, suggestion, or signaling information

No Comments

No Known Activations