INDEX

Explanations

terms associated with questions or inquiries

oai_token-act-pair · gpt-3.5-turbo

phrases that inquire about common or critical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

tex

-0.78

opens

-0.77

mares

-0.77

skirts

-0.76

camp

-0.75

icates

-0.74

nor

-0.73

arm

-0.72

usk

-0.71

forge

-0.70

POSITIVE LOGITS

?",

0.83

 motivating

0.73

 difference

0.73

 fuss

0.73

 holiest

0.70

?".

0.69

?,

0.69

 consolation

0.66

¬¼

0.66

?"

0.66

Activations Density 0.099%

terms associated with questions or inquiries

phrases that inquire about common or critical information

No Comments

No Known Activations