INDEX

Explanations

phrases related to flipping or turning

oai_token-act-pair · gpt-3.5-turbo

instances of the word "flip"

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

Negative Logits

 Territories

-0.81

Interstitial

-0.78

lain

-0.78

FORE

-0.70

mble

-0.69

needs

-0.66

CLA

-0.65

hart

-0.65

ãĤĮ

-0.64

Requires

-0.64

POSITIVE LOGITS

 flipped

0.91

 flip

0.90

 flipping

0.84

 flips

0.83

switch

0.82

 burgers

0.78

nir

0.78

wheel

0.76

 pancakes

0.75

flo

0.74

Activations Density 0.029%

phrases related to flipping or turning

instances of the word "flip"

No Known Activations