INDEX

Explanations

proper nouns and names of locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names of locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 unrem

-0.68

 unanswered

-0.66

ologically

-0.65

 unresolved

-0.65

cffffcc

-0.63

 unex

-0.62

 overt

-0.62

urg

-0.61

ikuman

-0.60

 aven

-0.60

POSITIVE LOGITS

 IMAGES

1.09

 Caption

1.01

 Researchers

0.94

↵

0.92

Buy

0.86

 Images

0.86

 Courtesy

0.85

↵Âł

0.85

Ltd

0.85

 Flickr

0.85

Activations Density 0.078%

proper nouns and names of locations

proper nouns, particularly names of locations and organizations

No Comments

No Known Activations