INDEX

Explanations

words related to logic and analysis, focusing on concepts related to abstraction, representation, and analytical systems

oai_token-act-pair · gpt-3.5-turbo

words related to notions of nationality or identity

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

ãģ®éŃĶ

-0.75

conom

-0.72

Bay

-0.71

Boss

-0.69

Santa

-0.67

Bone

-0.67

Brand

-0.65

San

-0.63

Nap

-0.63

Merc

-0.62

POSITIVE LOGITS

ational

1.12

ally

0.99

ized

0.99

ity

0.99

ities

0.99

ism

0.93

itÃ©

0.93

ists

0.92

 minded

0.91

ist

0.88

Activations Density 0.014%

words related to logic and analysis, focusing on concepts related to abstraction, representation, and analytical systems

words related to notions of nationality or identity

No Comments

No Known Activations