INDEX

Explanations

phrases related to specific names or terms

oai_token-act-pair · gpt-3.5-turbo

nouns and terms associated with people and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Conclusion

-0.66

?ãĢį

-0.66

 ********************************

-0.65

.ãĢį

-0.64

 Reply

-0.62

"?

-0.61

Advertisements

-0.61

.?

-0.60

udeb

-0.60

\">

-0.59

POSITIVE LOGITS

--

1.17

—

1.16

 âĢķ

1.11

–

0.97

0.96

0.85

—

0.84

,-

0.72

--

0.71

é¾įåĸļå£«

0.66

Activations Density 0.930%

phrases related to specific names or terms

nouns and terms associated with people and their relationships

No Comments

No Known Activations