INDEX

Explanations

adjectives related to the strength or importance of a particular issue or concept

oai_token-act-pair · gpt-3.5-turbo

terms that indicate intensity or severity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ilk

-0.91

ften

-0.74

claimer

-0.71

naire

-0.71

ologue

-0.71

 Puzzle

-0.71

washer

-0.69

UME

-0.68

ulhu

-0.68

ifice

-0.67

POSITIVE LOGITS

 amounts

1.40

 quantities

1.14

 doses

1.01

 indications

1.01

 levels

0.99

 advantages

0.99

 parallels

0.97

 similarities

0.95

 opportunities

0.94

 margins

0.93

Activations Density 0.278%

adjectives related to the strength or importance of a particular issue or concept

terms that indicate intensity or severity

No Comments

No Known Activations