INDEX

Explanations

technical terms and actions related to warfare and combat

oai_token-act-pair · gpt-3.5-turbo

actions and verbs related to social interactions and events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

initions

-0.68

},{"

-0.67

 Anger

-0.64

olutions

-0.64

 msec

-0.62

deals

-0.62

 Borders

-0.61

 Curve

-0.60

iage

-0.59

 Efficiency

-0.58

POSITIVE LOGITS

ed

1.41

ing

1.39

lessly

1.29

ned

1.22

edly

1.21

ioned

1.19

less

1.18

ning

1.18

lled

1.16

edIn

1.14

Activations Density 0.302%

technical terms and actions related to warfare and combat

actions and verbs related to social interactions and events

No Comments

No Known Activations