INDEX

Explanations

numerical identifiers such as identification numbers and list items

oai_token-act-pair · gpt-3.5-turbo

numeric identifiers or codes associated with various items or entries

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

 gain

-0.77

 pasture

-0.69

itably

-0.66

 gardens

-0.66

 graceful

-0.65

 countryside

-0.64

 halls

-0.64

 landscapes

-0.64

jog

-0.63

etimes

-0.62

POSITIVE LOGITS

CB

1.05

0.84

ä»£

0.79

Quality

0.78

DragonMagazine

0.76

0.75

Activations Density 0.033%

numerical identifiers such as identification numbers and list items

numeric identifiers or codes associated with various items or entries

No Comments

No Known Activations