INDEX

Explanations

phrases indicating a change or shift in something

oai_token-act-pair · gpt-3.5-turbo

references to changes 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Crunch

-0.74

KK

-0.74

Cru

-0.70

aturdays

-0.69

GGGGGGGG

-0.68

linger

-0.67

EEEE

-0.67

lees

-0.67

©¶æ¥µ

-0.65

Sure

-0.65

POSITIVE LOGITS

 favor

0.88

 favour

0.86

 fortunes

0.85

 scenery

0.84

 regards

0.83

version

0.82

 situ

0.82

animate

0.81

 circumstance

0.78

 circumstances

0.78

Activations Density 0.089%

phrases indicating a change or shift in something

references to changes in various contexts

No Comments

No Known Activations