INDEX

Explanations

references to food items, especially those related to chocolate and caramel

oai_token-act-pair · gpt-3.5-turbo

references to specific brands and types of food products, particularly sweets and snacks

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

NN

-0.70

ales

-0.69

xy

-0.68

alt

-0.67

ĩ

-0.67

 Jinping

-0.66

lar

-0.64

^^^^

-0.64

Builder

-0.64

printf

-0.64

POSITIVE LOGITS

âĢ¢âĢ¢âĢ¢âĢ¢

0.88

istically

0.80

mental

0.77

 Tasman

0.76

istic

0.76

amel

0.73

pelled

0.72

ciation

0.68

arette

0.67

 drib

0.66

Activations Density 0.045%

references to food items, especially those related to chocolate and caramel

references to specific brands and types of food products, particularly sweets and snacks

No Comments

No Known Activations