INDEX

Explanations

versions of the word "fashionista."

oai_token-act-pair · gpt-3.5-turbo

words related to "ista," indicating a focus on specialist or expert roles in various fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

MENTS

-0.84

shaw

-0.77

orate

-0.74

frames

-0.73

lying

-0.73

names

-0.72

ibble

-0.72

bred

-0.71

trak

-0.70

MENT

-0.70

POSITIVE LOGITS

ista

0.91

uthor

0.84

ignt

0.82

uto

0.80

 Libre

0.79

zzi

0.78

istas

0.77

da

0.76

 Rica

0.74

zza

0.74

Activations Density 0.009%

versions of the word "fashionista."

words related to "ista," indicating a focus on specialist or expert roles in various fields

No Comments

No Known Activations