INDEX

Explanations

phrases related to obtaining or granting permission

oai_token-act-pair · gpt-3.5-turbo

instances of the word "permission."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ulz

-0.84

 Scream

-0.75

tal

-0.73

bane

-0.68

ulative

-0.67

vae

-0.67

ÃŁ

-0.67

urgy

-0.65

tk

-0.65

nik

-0.65

POSITIVE LOGITS

 permission

1.34

 permissions

1.03

 waivers

0.85

 clearance

0.85

URI

0.83

uthor

0.83

 slips

0.82

 granted

0.82

Reviewer

0.81

 approvals

0.81

Activations Density 0.009%

phrases related to obtaining or granting permission

instances of the word "permission."

No Comments

No Known Activations