INDEX

Explanations

linguistics-related terms and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to linguistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Parties

-0.72

 McDonnell

-0.71

 Cycl

-0.65

 Agenda

-0.64

OHN

-0.64

 Views

-0.63

apego

-0.63

-0.62

 Valkyrie

-0.62

ride

-0.62

POSITIVE LOGITS

 lingu

1.41

anguage

1.02

istics

0.99

ingu

0.96

 challeng

0.95

ophone

0.93

lex

0.90

anguages

0.87

istically

0.86

tymology

0.83

Activations Density 0.009%

linguistics-related terms and concepts

terms related to linguistics

No Comments

No Known Activations