INDEX

Explanations

words related to emphasizing or underlining a point or idea

oai_token-act-pair · gpt-3.5-turbo

words related to the act of emphasizing or placing importance on something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

sil

-0.71

onew

-0.68

tumblr

-0.68

busters

-0.67

ston

-0.66

found

-0.65

abet

-0.65

izons

-0.64

running

-0.64

soever

-0.64

POSITIVE LOGITS

 emphasizing

0.94

 emphasized

0.86

 emphasizes

0.86

xual

0.85

 emphasize

0.82

 emphasis

0.77

 emphas

0.76

 contrasts

0.75

 shifts

0.74

imaru

0.73

Activations Density 0.013%

words related to emphasizing or underlining a point or idea

words related to the act of emphasizing or placing importance on something

No Comments

No Known Activations