INDEX

Explanations

promotions or deals offering rewards or benefits

oai_token-act-pair · gpt-3.5-turbo

phrases related to receiving benefits or rewards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

igr

-0.82

lie

-0.69

worthy

-0.64

eem

-0.63

Recomm

-0.61

abin

-0.61

bourne

-0.60

eli

-0.60

factor

-0.59

 fallacy

-0.58

POSITIVE LOGITS

rid

1.11

 reimb

1.03

 refunds

0.94

 preferential

0.94

 rewarded

0.92

 bumped

0.88

 access

0.87

 compensated

0.86

 paid

0.85

 unlimited

0.81

Activations Density 0.097%

promotions or deals offering rewards or benefits

phrases related to receiving benefits or rewards

No Comments

No Known Activations