INDEX

Explanations

words related to different countries

oai_token-act-pair · gpt-3.5-turbo

proper nouns and entities, particularly names of places or organizations

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

acre

-0.76

rag

-0.74

ternity

-0.73

ulty

-0.72

potion

-0.70

raviolet

-0.69

wt

-0.68

naissance

-0.66

prints

-0.66

uster

-0.66

POSITIVE LOGITS

 annexed

1.07

 borders

1.05

 nationals

1.04

 coast

1.03

 natives

1.01

 countries

0.98

 shores

0.98

ESE

0.97

 embassies

0.97

 coastline

0.97

Activations Density 0.766%

words related to different countries

proper nouns and entities, particularly names of places or organizations

No Comments

No Known Activations