INDEX

Explanations

locations or proper nouns related to the country Nepal

oai_token-act-pair · gpt-3.5-turbo

mentions of the country Nepal and related terms

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

=#

-0.74

istration

-0.72

 Painter

-0.69

aunder

-0.69

erie

-0.68

hement

-0.67

dinand

-0.67

positive

-0.67

\\\\\\\\\\\\\\\\

-0.66

tower

-0.64

POSITIVE LOGITS

 Pradesh

1.08

ayan

1.01

 Nepal

0.99

 Everest

0.81

 Airways

0.80

 Himal

0.78

aya

0.78

Nep

0.77

 Lanka

0.77

 Kath

0.76

Activations Density 0.020%

locations or proper nouns related to the country Nepal

mentions of the country Nepal and related terms

No Comments

No Known Activations