INDEX

Explanations

phrases where the words "the" and another word are close to each other

oai_token-act-pair · gpt-3.5-turbo

repetitive use of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

tackle

-0.89

anon

-0.71

thood

-0.71

=#

-0.69

adays

-0.68

quished

-0.68

iversal

-0.67

 again

-0.67

still

-0.66

CLA

-0.66

POSITIVE LOGITS

 slightest

1.31

 simplest

1.29

 smallest

1.16

 finest

1.09

 cheapest

1.06

 basics

1.04

 hars

1.00

 richest

0.98

 easiest

0.98

 wealthiest

0.98

Activations Density 0.152%

phrases where the words "the" and another word are close to each other

repetitive use of the word "the."

No Comments

No Known Activations