INDEX

Explanations

references to physical structures or landmarks, particularly with high significance or recognition

oai_token-act-pair · gpt-3.5-turbo

references to monuments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

Leary

-0.74

FP

-0.73

Roy

-0.68

rosso

-0.67

erm

-0.67

ENG

-0.65

lass

-0.64

Liquid

-0.64

tails

-0.63

ya

-0.63

POSITIVE LOGITS

 monuments

1.07

 monument

1.06

 erected

1.01

alist

0.87

vironment

0.81

wikipedia

0.78

arium

0.78

tyr

0.76

 plaque

0.76

olithic

0.75

Activations Density 0.029%

references to physical structures or landmarks, particularly with high significance or recognition

references to monuments

No Comments

No Known Activations