INDEX

Explanations

phrases related to learning something new or acquiring knowledge

oai_token-act-pair · gpt-3.5-turbo

instances of the word "learned" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

size

-0.74

 tilt

-0.71

NH

-0.67

pop

-0.66

burse

-0.65

url

-0.64

 Issue

-0.64

 entitle

-0.62

FX

-0.60

Support

-0.59

POSITIVE LOGITS

 learned

3.61

 learnt

2.91

 Learned

2.50

learn

2.17

 learns

2.05

 learn

1.83

 learning

1.63

Lear

1.63

 mastered

1.55

 taught

1.41

Activations Density 0.022%

phrases related to learning something new or acquiring knowledge

instances of the word "learned" and its variations

No Comments

No Known Activations