INDEX

Explanations

words related to important or sensitive topics or concepts

oai_token-act-pair · gpt-3.5-turbo

terms that indicate significance or urgency related to issues or concepts

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

ften

-0.73

thora

-0.71

phasis

-0.69

pload

-0.68

 onwards

-0.68

©¶æ

-0.66

ttle

-0.66

 tremend

-0.66

ilogy

-0.65

uncle

-0.65

POSITIVE LOGITS

 aspects

1.27

 situations

1.21

 areas

1.20

 topics

1.17

 technologies

1.17

 portions

1.16

 industries

1.15

 projects

1.14

ities

1.11

 facets

1.10

Activations Density 0.302%

words related to important or sensitive topics or concepts

terms that indicate significance or urgency related to issues or concepts

No Comments

No Known Activations