INDEX

Explanations

phrases related to specific locations

oai_token-act-pair · gpt-3.5-turbo

occurrences 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 @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

SPONSORED

-0.47

 âĢº

-0.47

âĢł

-0.47

.''

-0.47

eno

-0.46

 without

-0.46

antes

-0.46

ccoli

-0.45

ãĥ»

-0.45

 with

-0.45

POSITIVE LOGITS

 same

0.97

 latter

0.95

 aforementioned

0.93

 slightest

0.91

 entirety

0.88

 entire

0.86

 smallest

0.86

 remainder

0.86

 latest

0.84

 simplest

0.83

Activations Density 1.607%

phrases related to specific locations

occurrences of the word "the."

No Comments

No Known Activations