INDEX

Explanations

keywords related to online content or websites

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "OL" within various contexts or settings

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

flies

-0.93

ãĥ¼ãĥĨ

-0.85

fly

-0.78

ãĥ¼ãĥĨãĤ£

-0.77

ãĥ¥

-0.71

cia

-0.66

rament

-0.65

quo

-0.64

 germ

-0.64

ãĥ£

-0.63

POSITIVE LOGITS

TON

0.99

IX

0.99

ibrary

0.98

BY

0.97

UTION

0.96

ION

0.93

ONG

0.92

ARS

0.92

VIDIA

0.90

IFE

0.87

Activations Density 0.029%

keywords related to online content or websites

references to the concept of "OL" within various contexts or settings

No Comments

No Known Activations