INDEX

Explanations

adverbs modifying other words, particularly related to degree (e.g., "well", "far")

oai_token-act-pair · gpt-3.5-turbo

evaluative terms related to performance and distance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

:\

-0.78

ãĤ´ãĥ³

-0.73

baum

-0.72

actionDate

-0.71

nikov

-0.71

è£

-0.71

¶æ

-0.69

åĤ

-0.69

ãģĮ

-0.68

pez

-0.67

POSITIVE LOGITS

vou

0.76

 they

0.75

 elapsed

0.72

 awaited

0.71

 invested

0.71

we

0.67

 millenn

0.66

 streamed

0.65

 militar

0.64

 fired

0.64

Activations Density 0.048%

adverbs modifying other words, particularly related to degree (e.g., "well", "far")

evaluative terms related to performance and distance

No Comments

No Known Activations