INDEX

Explanations

claims or statements that are unsupported or unsubstantiated

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 actionGroup

-0.90

ktop

-0.76

isites

-0.74

itaire

-0.72

ivation

-0.72

ahime

-0.70

 mobility

-0.69

ivating

-0.69

rontal

-0.68

itect

-0.68

POSITIVE LOGITS

 debunked

1.30

 falsehood

1.23

 assertions

1.20

False

1.18

Claim

1.14

 debunk

1.13

 untrue

1.13

 misinformation

1.13

 baseless

1.11

 claims

1.10

Activations Density 0.587%

claims or statements that are unsupported or unsubstantiated

No Comments

No Known Activations