INDEX

Explanations

keywords related to selections or recommendations such as "Picks."

oai_token-act-pair · gpt-3.5-turbo

references to "Picks" or curated selections in a document

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

lia

-0.81

acion

-0.72

gal

-0.72

igi

-0.69

 interf

-0.68

gur

-0.67

stood

-0.67

reek

-0.67

rel

-0.65

flying

-0.65

POSITIVE LOGITS

 Picks

1.42

ettings

0.82

leep

0.76

 Deadly

0.75

 Lists

0.73

 Annotations

0.73

essors

0.70

ļéĨĴ

0.68

 Moments

0.68

 Cheap

0.67

Activations Density 0.008%

keywords related to selections or recommendations such as "Picks."

references to "Picks" or curated selections in a document

No Comments

No Known Activations