INDEX

Explanations

phrases related to probability or likelihood

oai_token-act-pair · gpt-3.5-turbo

phrases indicating probabilities or chances of various outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 ILCS

-0.93

minus

-0.88

geist

-0.80

umbers

-0.78

umbered

-0.76

zek

-0.74

ahime

-0.72

ngth

-0.71

FactoryReloaded

-0.71

entric

-0.70

POSITIVE LOGITS

 encountering

1.30

 succeeding

1.30

 obtaining

1.30

 achieving

1.26

 success

1.18

 surviving

1.18

 getting

1.18

 winning

1.17

 acquiring

1.15

 catching

1.13

Activations Density 0.134%

phrases related to probability or likelihood

phrases indicating probabilities or chances of various outcomes

No Comments

No Known Activations