INDEX

Explanations

words related to various types of care, ranging from medical care to animal care

oai_token-act-pair · gpt-3.5-turbo

references to healthcare and medical care

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kered

-0.79

ãĥĥãĥī

-0.75

onite

-0.72

ãĥ³ãĤ¸

-0.70

 bluff

-0.67

âĸ¬

-0.67

 rand

-0.61

 grease

-0.60

akedown

-0.60

è¦ļéĨĴ

-0.60

POSITIVE LOGITS

taker

1.50

giving

1.29

taking

1.11

lessly

1.07

tta

1.03

fully

0.99

lessness

0.96

lington

0.91

ening

0.90

ful

0.87

Activations Density 0.024%

words related to various types of care, ranging from medical care to animal care

references to healthcare and medical care

No Comments

No Known Activations