INDEX

Explanations

locations and countries, particularly focusing on the Czech Republic

oai_token-act-pair · gpt-3.5-turbo

references to the Czech Republic and its capital city, Prague

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

natureconservancy

-0.92

ciating

-0.88

nels

-0.78

cule

-0.78

utherford

-0.74

aeda

-0.74

LEASE

-0.71

htar

-0.70

ufact

-0.70

inventoryQuantity

-0.68

POSITIVE LOGITS

oslov

2.05

oslav

1.17

 Republic

1.13

ski

0.91

istani

0.86

Republic

0.83

sky

0.81

0.78

sis

0.77

sylvania

0.77

Activations Density 0.018%

locations and countries, particularly focusing on the Czech Republic

references to the Czech Republic and its capital city, Prague

No Comments

No Known Activations