INDEX

Explanations

instances where the word "Modern" appears

oai_token-act-pair · gpt-3.5-turbo

references to "Modern" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avering

-0.95

cial

-0.78

GV

-0.75

vana

-0.72

INO

-0.70

cific

-0.70

INESS

-0.69

RAY

-0.68

 exact

-0.67

--------------------------------------------------------

-0.66

POSITIVE LOGITS

 Modern

0.96

ieval

0.93

modern

0.90

odon

0.88

 sensibilities

0.83

 Warfare

0.82

antine

0.80

Modern

0.77

glers

0.75

Era

0.74

Activations Density 0.008%

instances where the word "Modern" appears

references to "Modern" in various contexts

No Comments

No Known Activations