INDEX

Explanations

statistics or quantitative information within text

oai_token-act-pair · gpt-3.5-turbo

references to additional information or elaboration on a topic

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ãĥ¼ãĥĨãĤ£

-0.86

ãĤ©

-0.78

ãĤ£

-0.66

mir

-0.66

ãĥĨãĤ£

-0.61

 Columb

-0.60

asus

-0.60

ãĥ¥

-0.60

eg

-0.59

Border

-0.59

POSITIVE LOGITS

 VIDEOS

0.81

enegger

0.80

ellen

0.77

eat

0.69

illard

0.67

brainer

0.66

enthal

0.66

*/(

0.66

omo

0.64

entially

0.64

Activations Density 0.017%

statistics or quantitative information within text

references to additional information or elaboration on a topic

No Comments

No Known Activations