INDEX

Explanations

single-letter words that are used as articles

oai_token-act-pair · gpt-3.5-turbo

instances of the word "a" indicating the presence of articles

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

Versions

-0.85

alties

-0.80

uin

-0.78

effects

-0.76

['

-0.74

anism

-0.73

isms

-0.71

properties

-0.71

lime

-0.71

culosis

-0.70

POSITIVE LOGITS

 huge

1.03

 HUGE

1.03

 continuation

1.00

 blatant

0.97

 fascinating

0.97

 reminder

0.96

 hypothetical

0.95

 difficult

0.93

 tricky

0.92

 monumental

0.92

Activations Density 0.113%

single-letter words that are used as articles

instances of the word "a" indicating the presence of articles

No Comments

No Known Activations