INDEX

Explanations

phrases related to advertising

oai_token-act-pair · gpt-3.5-turbo

instances of advertisements in the text

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

Kut

-0.74

ker

-0.70

Klu

-0.69

joy

-0.69

 motivating

-0.68

 Prometheus

-0.66

pled

-0.65

joy

-0.64

rek

-0.64

bred

-0.63

POSITIVE LOGITS

ADVERTISEMENT

1.13

iciary

0.92

Skip

0.90

interstitial

0.85

VERTISEMENT

0.83

 VIDEOS

0.81

 Continued

0.77

dinand

0.76

inarily

0.76

 Appears

0.75

Activations Density 0.010%

phrases related to advertising

instances of advertisements in the text

No Comments

No Known Activations