INDEX

Explanations

proper nouns or names of people and places

oai_token-act-pair · gpt-3.5-turbo

repeated phrases indicating an alternative name or title for subjects

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

eways

-0.74

assian

-0.68

vantage

-0.67

legraph

-0.67

iotic

-0.67

ihara

-0.66

othal

-0.65

eff

-0.64

eway

-0.63

benefit

-0.61

POSITIVE LOGITS

 nicknamed

1.05

 known

1.01

 renamed

0.89

 dubbed

0.87

 spelled

0.86

 referred

0.84

 abbre

0.77

 marketed

0.76

known

0.76

 styled

0.76

Activations Density 0.106%

proper nouns or names of people and places

repeated phrases indicating an alternative name or title for subjects

No Comments

No Known Activations