INDEX

Explanations

keywords related to closing statements or conclusions

oai_token-act-pair · gpt-3.5-turbo

phrases that contain the word "close."

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

Negative Logits

ologically

-0.83

urg

-0.76

unal

-0.73

osc

-0.72

uana

-0.69

olog

-0.68

urally

-0.67

otropic

-0.67

war

-0.66

oscope

-0.66

POSITIVE LOGITS

CLOSE

1.60

 Skip

0.91

berries

0.82

aign

0.80

FIX

0.79

PLIED

0.78

atchewan

0.77

GROUND

0.76

sburgh

0.74

Skip

0.74

Activations Density 0.013%

keywords related to closing statements or conclusions

phrases that contain the word "close."

No Known Activations