INDEX

Explanations

phrases that indicate comparison or opposition

oai_token-act-pair · gpt-3.5-turbo

words and phrases indicating measurement or comparison

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owder

-0.67

achev

-0.67

%%

-0.65

utenberg

-0.62

 Started

-0.60

Synopsis

-0.60

 sugg

-0.60

hemer

-0.59

CVE

-0.58

Material

-0.58

POSITIVE LOGITS

 elsewhere

1.17

 others

1.14

 other

1.08

 neighbouring

0.97

 Others

0.93

 ours

0.90

Others

0.86

 neighboring

0.86

other

0.83

 Other

0.81

Activations Density 1.459%

phrases that indicate comparison or opposition

words and phrases indicating measurement or comparison

No Comments

No Known Activations