INDEX

Explanations

questions starting with the word "Why"

oai_token-act-pair · gpt-3.5-turbo

the end of sections and questions posed in the text

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 slightest

-0.71

 hereafter

-0.68

Â¯

-0.68

office

-0.65

artifacts

-0.64

guard

-0.63

fm

-0.62

wcs

-0.62

Interstitial

-0.61

general

-0.61

POSITIVE LOGITS

 Does

1.06

 Exactly

0.99

 Makes

0.90

 Difference

0.87

 Popular

0.86

 Develop

0.85

Own

0.85

Did

0.84

 Benefits

0.84

quickShipAvailable

0.83

Activations Density 0.074%

questions starting with the word "Why"

the end of sections and questions posed in the text

No Comments

No Known Activations