INDEX

Explanations

phrases related to the concept of "meaning"

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "meaning."

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asting

-0.70

aliation

-0.70

iets

-0.68

culosis

-0.67

emetery

-0.67

thumbnails

-0.66

interstitial

-0.62

 Breed

-0.62

nih

-0.62

Monitor

-0.62

POSITIVE LOGITS

fully

1.47

ful

1.19

fulness

1.19

lessness

1.18

bringer

0.93

FUL

0.85

lessly

0.85

sworth

0.83

notations

0.80

 Meaning

0.80

Activations Density 0.025%

phrases related to the concept of "meaning"

references to the concept of "meaning."

No Comments

No Known Activations