INDEX

Explanations

phrases related to emphasizing or highlighting important points or concepts

oai_token-act-pair · gpt-3.5-turbo

key phrases indicating necessity or importance 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soever

-0.88

Edit

-0.71

 Stephanie

-0.69

 Fraz

-0.67

ansas

-0.65

 Psychiat

-0.65

????

-0.65

Track

-0.64

 Shaun

-0.64

 Linda

-0.63

POSITIVE LOGITS

 importance

1.49

 existence

1.29

 impossibility

1.27

 possibility

1.23

 superiority

1.18

 presence

1.12

 validity

1.11

 usefulness

1.10

 seriousness

1.10

 necessity

1.09

Activations Density 0.303%

phrases related to emphasizing or highlighting important points or concepts

key phrases indicating necessity or importance in various contexts

No Comments

No Known Activations