INDEX

Explanations

text separators or formatting markers

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude and warmth

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

 Doll

-0.73

hement

-0.71

 destro

-0.71

 Learns

-0.70

bom

-0.69

 Magicka

-0.64

Ley

-0.64

 charism

-0.64

 Ingredients

-0.63

 Shell

-0.62

POSITIVE LOGITS

Î³

0.92

andro

0.86

voy

0.84

bus

0.84

eport

0.81

heter

0.81

nu

0.79

ItemThumbnailImage

0.79

soDeliveryDate

0.78

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.77

Activations Density 0.085%

text separators or formatting markers

expressions of gratitude and warmth

No Comments

No Known Activations