INDEX

Explanations

the word "see" in various contexts

oai_token-act-pair · gpt-3.5-turbo

expressions of perception or viewpoint regarding situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 withd

-0.66

ÃŃa

-0.64

eware

-0.64

ium

-0.63

 whistle

-0.62

cÃ©

-0.61

 anthem

-0.61

 agric

-0.59

 voyage

-0.58

Tweet

-0.58

POSITIVE LOGITS

 parallels

0.95

WARD

0.84

awed

0.79

 similarities

0.77

ĸ

0.76

Ĺ

0.73

 positives

0.72

¿½

0.71

Ĭ±

0.70

poke

0.69

Activations Density 0.068%

the word "see" in various contexts

expressions of perception or viewpoint regarding situations

No Comments

No Known Activations