INDEX

Explanations

phrases related to the abbreviation 'AC'

oai_token-act-pair · gpt-3.5-turbo

mentions of "AC" related to a specific context or topic

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

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

ãĥĦ

-0.76

 Fenrir

-0.74

glers

-0.71

ozyg

-0.71

doms

-0.70

jar

-0.69

lihood

-0.68

 Tradable

-0.68

cake

-0.68

heimer

-0.67

POSITIVE LOGITS

oustic

0.98

oust

0.96

ORN

0.95

rylic

0.93

CEPT

0.87

ros

0.84

upuncture

0.83

olor

0.80

HE

0.79

ritical

0.79

Activations Density 0.009%

phrases related to the abbreviation 'AC'

mentions of "AC" related to a specific context or topic

No Comments

No Known Activations