INDEX

Explanations

verbs related to achieving goals or completing tasks

oai_token-act-pair · gpt-3.5-turbo

terms related to achieving goals or completing tasks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

lights

-0.81

creen

-0.75

reen

-0.72

bane

-0.71

otin

-0.71

arth

-0.66

 tyres

-0.66

olson

-0.66

corn

-0.66

den

-0.64

POSITIVE LOGITS

 accomplish

1.00

 accomplished

0.93

issance

0.86

 accompl

0.81

 accomplishment

0.78

ments

0.77

iage

0.75

å¥³

0.73

llor

0.70

omething

0.70

Activations Density 0.018%

verbs related to achieving goals or completing tasks

terms related to achieving goals or completing tasks

No Comments

No Known Activations