INDEX

Explanations

phrases instructing or informing the user to take specific actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "you" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aberdeen

-0.74

 Canaver

-0.71

 Aber

-0.65

atur

-0.65

 Chap

-0.62

 Cabin

-0.62

enges

-0.62

 Kang

-0.62

 Mane

-0.62

 Defenders

-0.61

POSITIVE LOGITS

're

1.37

've

1.20

'll

1.16

'd

0.92

may

0.89

can

0.86

RS

0.85

 cannot

0.83

 MUST

0.80

 know

0.78

Activations Density 0.060%

phrases instructing or informing the user to take specific actions

instances of the word "you" in various contexts

No Comments

No Known Activations