INDEX

Explanations

instances where "smile" is mentioned in different contexts

oai_token-act-pair · gpt-3.5-turbo

references to smiling or expressions of happiness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

æ©Ł

-0.83

ferred

-0.69

aer

-0.67

 Administ

-0.66

unes

-0.65

lay

-0.65

inventoryQuantity

-0.64

FER

-0.63

raped

-0.62

forums

-0.61

POSITIVE LOGITS

 smile

1.03

 smiles

0.93

 hello

0.89

creen

0.89

 grin

0.89

 goodbye

0.87

 smiling

0.83

heet

0.77

eful

0.74

 emot

0.74

Activations Density 0.010%

instances where "smile" is mentioned in different contexts

references to smiling or expressions of happiness

No Comments

No Known Activations