INDEX

Explanations

words related to criticism or negative evaluations

oai_token-act-pair · gpt-3.5-turbo

terms related to negativity and negative concepts

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

BuyableInstoreAndOnline

-0.86

ORGE

-0.84

DragonMagazine

-0.76

Bloom

-0.76

è¦ļéĨĴ

-0.75

realDonaldTrump

-0.73

ä¹ĭ

-0.70

ãģ®å®

-0.69

WHERE

-0.69

PLA

-0.69

POSITIVE LOGITS

oti

1.45

otiation

1.44

atives

1.20

neg

1.04

rito

1.00

lect

0.99

ativity

0.96

atively

0.93

lected

0.89

rals

0.87

Activations Density 0.020%

words related to criticism or negative evaluations

terms related to negativity and negative concepts

No Comments

No Known Activations