INDEX

Explanations

instances of confusion or being confused in text

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Janeiro

-0.68

heimer

-0.67

conn

-0.63

 orchestra

-0.63

die

-0.61

 promot

-0.61

baugh

-0.61

Die

-0.61

 Derby

-0.60

tten

-0.60

POSITIVE LOGITS

ingly

0.91

 bewild

0.83

 confuse

0.80

lement

0.77

 confusing

0.76

ly

0.76

 confused

0.72

 confusion

0.72

 misunderstanding

0.71

 indist

0.71

Activations Density 0.103%

instances of confusion or being confused in text

No Comments

No Known Activations