INDEX

Explanations

words related to seeking or obtaining official permission or consent

oai_token-act-pair · gpt-3.5-turbo

instances of the word "approval" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hed

-0.84

hester

-0.81

 Canaver

-0.80

gm

-0.75

hematic

-0.75

nov

-0.73

ottesville

-0.71

enegger

-0.69

axies

-0.69

mers

-0.68

POSITIVE LOGITS

 rating

1.03

 approvals

1.00

 ratings

0.98

 approval

0.93

 process

0.87

 clearance

0.85

 waivers

0.85

worthy

0.85

 decree

0.82

 commissions

0.82

Activations Density 0.044%

words related to seeking or obtaining official permission or consent

instances of the word "approval" in various contexts

No Comments

No Known Activations