INDEX

Explanations

words that end in "-ose"

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "disease" or "illness"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ersen

-0.81

agne

-0.73

icum

-0.71

rators

-0.69

rade

-0.68

iage

-0.67

ADE

-0.66

oola

-0.65

enburg

-0.65

azon

-0.65

POSITIVE LOGITS

idon

1.12

velt

1.11

cond

1.06

lihood

1.02

lect

0.99

eker

0.92

LECT

0.91

ï¸

0.84

vich

0.83

ph

0.81

Activations Density 0.037%

words that end in "-ose"

terms related to the concept of "disease" or "illness"

No Comments

No Known Activations