INDEX

Explanations

phrases related to providing explanations or justifications

oai_token-act-pair · gpt-3.5-turbo

phrases related to explanations or justifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 stocking

-0.75

 puck

-0.70

iky

-0.66

ymph

-0.66

ouk

-0.65

lip

-0.65

annis

-0.65

 Roller

-0.64

thus

-0.64

elve

-0.63

POSITIVE LOGITS

why

1.18

WHY

1.08

why

0.93

 reason

0.91

abl

0.84

DragonMagazine

0.83

 justification

0.82

reason

0.81

FORE

0.81

 rationale

0.80

Activations Density 0.022%

phrases related to providing explanations or justifications

phrases related to explanations or justifications

No Comments

No Known Activations