INDEX

Explanations

phrases related to causes and effects, especially leading to a significant outcome

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

milo

-0.82

VERTISEMENT

-0.78

dden

-0.75

arrow

-0.74

ahime

-0.72

np

-0.70

gyn

-0.69

rx

-0.69

ngth

-0.68

igans

-0.68

POSITIVE LOGITS

 creation

1.47

 removal

1.45

 resignation

1.43

 imposition

1.37

 elimination

1.35

 formation

1.33

 emergence

1.30

 cancellation

1.29

 introduction

1.26

 establishment

1.26

Activations Density 0.232%

phrases related to causes and effects, especially leading to a significant outcome

occurrences of the word "the" in various contexts

No Comments

No Known Activations

phrases related to causes and effects, especially leading to a significant outcome

occurrences of the word "the" in various contexts

No Comments

No Known Activations