INDEX

Explanations

phrases related to requesting, providing, or offering assistance

oai_token-act-pair · gpt-3.5-turbo

instances of the word "assistance" and related concepts of help and support

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

aval

-0.77

bish

-0.74

nu

-0.73

Benz

-0.71

 Schmidt

-0.71

tail

-0.69

 Beard

-0.68

bane

-0.67

 Chern

-0.67

Compar

-0.66

POSITIVE LOGITS

 assistance

1.10

aid

0.98

aid

0.87

 recip

0.87

 aids

0.86

 Assistance

0.85

 assisting

0.83

enza

0.83

assisted

0.82

 assist

0.81

Activations Density 0.010%

phrases related to requesting, providing, or offering assistance

instances of the word "assistance" and related concepts of help and support

No Comments

No Known Activations