INDEX

Explanations

locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

geographic locations and their representations

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

Torrent

-0.67

 bumper

-0.66

BOOK

-0.64

 Gravity

-0.63

ufact

-0.59

-0.58

ãĥĳ

-0.57

 ante

-0.56

ãĤ½

-0.55

 critical

-0.54

POSITIVE LOGITS

jer

0.78

isco

0.72

oland

0.72

jri

0.71

.,

0.71

 Lumpur

0.68

 Rapids

0.67

gart

0.67

quartered

0.67

mx

0.65

Activations Density 0.119%

locations mentioned in news articles

geographic locations and their representations

No Comments

No Known Activations