INDEX

Explanations

proper nouns, specifically names of locations and organizations

oai_token-act-pair · gpt-3.5-turbo

names of places or notable entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

PDATE

-0.81

 Adin

-0.74

PsyNetMessage

-0.71

 referen

-0.71

displayText

-0.65

 Enrique

-0.64

ĸļ

-0.63

Bloomberg

-0.63

 Sina

-0.62

 advant

-0.61

POSITIVE LOGITS

 Productions

1.14

 Studios

1.05

 Farms

0.94

 Syndrome

0.93

atoes

0.92

 Records

0.84

 Laboratories

0.84

 Brewery

0.84

 Orchestra

0.82

 Massacre

0.81

Activations Density 0.367%

proper nouns, specifically names of locations and organizations

names of places or notable entities

No Comments

No Known Activations