INDEX

Explanations

question phrases or inquiries

oai_token-act-pair · gpt-3.5-turbo

expressions related to explanation and uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

anwhile

-0.56

gerald

-0.51

etheus

-0.49

 Ambro

-0.49

safety

-0.48

 scrut

-0.48

alogue

-0.47

 elig

-0.47

ogether

-0.46

luster

-0.46

POSITIVE LOGITS

[+

0.68

](

0.63

 Â·

0.61

(@

0.61

 ðŁ

0.61

 ðŁĳ

0.60

 âĢ

0.59

É

0.59

 âľ

0.58

Activations Density 2.720%

question phrases or inquiries

expressions related to explanation and uncertainty

No Comments

No Known Activations