INDEX

Explanations

instances where permission is granted or requested

oai_token-act-pair · gpt-3.5-turbo

phrases related to granting permission or approval for actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ï¸ı

-0.94

lehem

-0.74

 Adin

-0.73

warts

-0.70

nces

-0.69

Peb

-0.66

together

-0.65

een

-0.63

chanted

-0.63

ngth

-0.62

POSITIVE LOGITS

 licences

0.79

 authorizing

0.77

 sale

0.76

 issuance

0.76

 renewal

0.76

 occupancy

0.75

 airspace

0.75

 permitting

0.72

 leasing

0.71

Reviewer

0.67

Activations Density 0.211%

instances where permission is granted or requested

phrases related to granting permission or approval for actions

No Comments

No Known Activations