INDEX

Explanations

phrases related to actions involving being monitored or investigated

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "for" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GREEN

-0.63

marine

-0.63

illin

-0.63

orbit

-0.62

fleet

-0.62

pointer

-0.59

Strange

-0.59

 Aviv

-0.59

Champ

-0.57

 sadd

-0.57

POSITIVE LOGITS

geries

1.21

gery

1.06

bidden

1.00

gotten

0.99

 purposes

0.91

 decades

0.88

cible

0.86

aging

0.84

 instance

0.83

 awhile

0.83

Activations Density 0.216%

phrases related to actions involving being monitored or investigated

phrases that include the word "for" in various contexts

No Comments

No Known Activations