INDEX

Explanations

unintelligible or nonsensical words

oai_token-act-pair · gpt-3.5-turbo

words related to expressions of confusion or nonsense

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

ItemThumbnailImage

-0.77

DragonMagazine

-0.76

 guiActiveUn

-0.70

interstitial

-0.69

iral

-0.64

SPONSORED

-0.64

 saturation

-0.63

 univers

-0.63

 latitude

-0.63

 accessibility

-0.62

POSITIVE LOGITS

chest

0.82

plate

0.78

pee

0.78

ashtra

0.78

atin

0.77

chet

0.77

bone

0.76

nuts

0.76

owl

0.75

hurst

0.74

Activations Density 0.353%

unintelligible or nonsensical words

words related to expressions of confusion or nonsense

No Comments

No Known Activations