INDEX

Explanations

legal or rule-related terms, and also potential threats or offenses

oai_token-act-pair · gpt-3.5-turbo

instances of formal declarations or legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilogy

-0.68

 Paddock

-0.65

enture

-0.64

ciples

-0.64

 Palmer

-0.63

knit

-0.62

 figure

-0.61

anchester

-0.60

utherland

-0.60

ocket

-0.59

POSITIVE LOGITS

 dishon

0.96

 unacceptable

0.95

 unworthy

0.86

 fail

0.86

Invalid

0.86

 disgrace

0.85

Failure

0.85

 discredit

0.83

 unfit

0.83

 failure

0.82

Activations Density 0.759%

legal or rule-related terms, and also potential threats or offenses

instances of formal declarations or legal terminology

No Comments

No Known Activations