INDEX

Explanations

proper nouns, specifically names and locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and terms associated with people and events

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

Shot

-0.78

ADS

-0.75

Rail

-0.75

Charg

-0.72

Charge

-0.71

Access

-0.71

Rush

-0.68

Stock

-0.67

 Anthem

-0.67

SPONSORED

-0.66

POSITIVE LOGITS

eg

1.29

ugu

0.81

Eg

0.79

 tong

0.79

omez

0.77

inkle

0.77

allery

0.76

ocent

0.75

ego

0.75

uration

0.74

Activations Density 0.006%

proper nouns, specifically names and locations

proper nouns, particularly names and terms associated with people and events

No Comments

No Known Activations