INDEX

Explanations

phrases comparing quantity or degree

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "less."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

DK

-0.73

ULE

-0.71

Grab

-0.71

 Events

-0.68

âĹ¼

-0.68

 Sequence

-0.68

Draft

-0.68

 Properties

-0.67

Disclaimer

-0.66

TRY

-0.66

POSITIVE LOGITS

 than

1.17

ened

0.98

ening

0.96

 forgiving

0.82

 conspicuous

0.81

 intrusive

0.79

 costly

0.75

thumbnails

0.74

 glamorous

0.73

 invasive

0.72

Activations Density 0.040%

phrases comparing quantity or degree

mentions of the word "less."

No Comments

No Known Activations