INDEX

Explanations

Spanish words included in text

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to locations or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bucks

-0.77

yip

-0.70

ufact

-0.70

 Roundup

-0.69

 tremend

-0.63

 chase

-0.62

 Takeru

-0.61

 counterfeit

-0.60

oppable

-0.60

 Achievements

-0.59

POSITIVE LOGITS

ternal

0.78

igham

0.76

estial

0.73

bral

0.72

ortium

0.72

efe

0.68

ula

0.67

RAL

0.66

irin

0.65

alid

0.64

Activations Density 0.163%

Spanish words included in text

abbreviations and acronyms related to locations or entities

No Comments

No Known Activations