INDEX

Explanations

phrases related to a specific date

oai_token-act-pair · gpt-3.5-turbo

the word "was" 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 @ 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

stood

-0.70

 newsletters

-0.69

inas

-0.68

arta

-0.68

veland

-0.65

 Millions

-0.65

inav

-0.64

 Mountains

-0.64

bys

-0.64

 HAVE

-0.63

POSITIVE LOGITS

hes

1.27

wolves

1.07

wolf

0.99

 originally

0.98

 conceived

0.96

 born

0.95

 instrumental

0.93

nt

0.92

 deemed

0.91

 initially

0.91

Activations Density 0.428%

phrases related to a specific date

the word "was" in various contexts

No Comments

No Known Activations