INDEX

Explanations

phrases related to flipping or turning something over

oai_token-act-pair · gpt-3.5-turbo

phrases that involve the action of "flipping."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Territories

-0.77

lain

-0.74

Interstitial

-0.72

mble

-0.71

FORE

-0.70

aph

-0.66

aining

-0.66

Requires

-0.65

needs

-0.64

hart

-0.63

POSITIVE LOGITS

 flipped

0.99

 flip

0.97

 flips

0.88

 flipping

0.85

switch

0.85

flo

0.79

wheel

0.78

 burgers

0.76

tera

0.76

 toss

0.76

Activations Density 0.022%

phrases related to flipping or turning something over

phrases that involve the action of "flipping."

No Comments

No Known Activations