INDEX

Explanations

technology-related terms and product names

oai_token-act-pair · gpt-3.5-turbo

specific brand or product names

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

rez

-0.68

ãĥĥ

-0.65

bear

-0.63

ãĤ®

-0.63

bi

-0.62

ãĥĥãĤ¯

-0.60

science

-0.60

wcs

-0.60

 Benz

-0.60

minecraft

-0.59

POSITIVE LOGITS

 Productions

0.81

 Plaza

0.76

 Saga

0.75

 Syndrome

0.75

 Generator

0.75

 Redemption

0.72

 Tokens

0.71

âĦ¢:

0.71

 Presents

0.71

 CafÃ©

0.70

Activations Density 0.225%

technology-related terms and product names

specific brand or product names

No Comments

No Known Activations