INDEX

Explanations

references to specific years labeled as "AD" in historical contexts

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

terms related to advertising or marketing, specifically focusing on the abbreviation "AD"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĸļ

-1.00

ãĤ¡

-0.74

htt

-0.72

assetsadobe

-0.70

awaru

-0.67

drop

-0.67

 Parenthood

-0.66

Ń·

-0.64

Wem

-0.63

 Kubrick

-0.62

POSITIVE LOGITS

VERTISEMENT

1.35

vantage

1.08

MIN

1.02

venture

1.02

VERTIS

1.01

minist

1.00

vance

0.94

visor

0.88

olph

0.88

olf

0.87

Activations Density 0.012%

references to specific years labeled as "AD" in historical contexts

terms related to advertising or marketing, specifically focusing on the abbreviation "AD"

No Comments

No Known Activations