INDEX

Explanations

phrases related to increasing or escalating actions or quantities

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate an increase in quantity or limits

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mire

-0.73

gnu

-0.72

kef

-0.69

ouse

-0.69

brook

-0.66

alus

-0.65

mong

-0.64

 Saul

-0.64

english

-0.64

CENT

-0.63

POSITIVE LOGITS

 intensity

1.15

 amount

1.13

 severity

1.08

 likelihood

1.08

 effectiveness

1.07

 incidence

1.03

 allowable

0.99

 size

0.98

 burden

0.97

 number

0.96

Activations Density 0.185%

phrases related to increasing or escalating actions or quantities

phrases that indicate an increase in quantity or limits

No Comments

No Known Activations