INDEX

Explanations

water-related words or phrases

oai_token-act-pair · gpt-3.5-turbo

phrases and terms associated with water and its properties

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

elligent

-0.73

IX

-0.71

KK

-0.69

«ĺ

-0.69

Ko

-0.68

IJ

-0.67

:{

-0.67

 acknow

-0.66

iscopal

-0.65

Student

-0.65

POSITIVE LOGITS

 dams

0.83

 wastewater

0.80

 oats

0.80

 electroly

0.80

 gravel

0.77

 reservoirs

0.76

 humid

0.75

 minerals

0.71

 irrig

0.71

 wast

0.71

Activations Density 0.473%

water-related words or phrases

phrases and terms associated with water and its properties

No Comments

No Known Activations