INDEX

Explanations

phrases related to attempts or efforts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

plates

-0.71

 Used

-0.68

 Appears

-0.68

 Compass

-0.67

houses

-0.66

shown

-0.66

 Cros

-0.65

 Spaces

-0.64

requires

-0.64

 Begins

-0.63

POSITIVE LOGITS

 emulate

1.25

 recreate

1.16

 imitate

1.14

 avoid

1.12

 improve

1.10

 defend

1.08

 penetrate

1.07

 minimize

1.06

 solve

1.06

 evade

1.05

Activations Density 0.159%

phrases related to attempts or efforts

instances of the word "to."

No Comments

No Known Activations