INDEX

Explanations

phrases related to advertisements or promotional content

oai_token-act-pair · gpt-3.5-turbo

references to "AD" followed by numerical values, which likely relate to specific identifiers or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

htt

-0.72

assetsadobe

-0.69

 Kubrick

-0.68

 Stronghold

-0.64

ĸļ

-0.61

 externalToEVAOnly

-0.61

 Trog

-0.60

Kus

-0.58

tons

-0.58

 Yiannopoulos

-0.57

POSITIVE LOGITS

VERTIS

1.27

VERTISEMENT

1.23

MIN

1.16

vantage

1.08

venture

1.02

DIS

0.99

visor

0.99

DR

0.98

iamond

0.96

ILY

0.94

Activations Density 0.026%

phrases related to advertisements or promotional content

references to "AD" followed by numerical values, which likely relate to specific identifiers or categories

No Comments

No Known Activations