INDEX

Explanations

proper nouns, especially names likely associated with various individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and terms related to particular names or concepts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

cook

-0.76

olerance

-0.75

OPLE

-0.74

phrine

-0.73

step

-0.72

KEN

-0.69

 Handler

-0.69

eco

-0.68

 Raider

-0.68

watch

-0.67

POSITIVE LOGITS

icles

1.22

icle

1.10

icular

0.98

rha

0.89

itational

0.87

oras

0.87

ora

0.87

ilion

0.85

rix

0.85

ricular

0.81

Activations Density 0.017%

proper nouns, especially names likely associated with various individuals

proper nouns and terms related to particular names or concepts

No Known Activations