INDEX

Explanations

terms related to achievements or recognition such as awards or prizes

oai_token-act-pair · gpt-3.5-turbo

terms related to awards and recognition

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

é¾įå¥ĳå£«

-0.83

 pron

-0.60

rawdownloadcloneembedreportprint

-0.60

MIL

-0.55

 Pale

-0.55

 Shack

-0.54

 interchange

-0.54

 unsupported

-0.53

less

-0.53

 Wine

-0.52

POSITIVE LOGITS

ª

1.05

¹

1.00

·

1.00

©

0.99

´

0.99

Ģ

0.99

ĩ

0.99

¬

0.98

¼

0.94

ħ

0.94

Activations Density 0.377%

terms related to achievements or recognition such as awards or prizes

terms related to awards and recognition

No Comments

No Known Activations