INDEX

Explanations

statements commanding someone to do something

oai_token-act-pair · gpt-3.5-turbo

repetitions 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

VERTISEMENT

-0.87

lived

-0.82

hazard

-0.74

illac

-0.73

estyles

-0.73

icut

-0.72

ãĥł

-0.72

ãĥĬ

-0.72

ãĥ¡

-0.71

Interstitial

-0.71

POSITIVE LOGITS

 audience

1.06

 reader

1.03

 interviewer

1.02

 listeners

0.94

 dispatcher

0.93

 populace

0.92

 waiter

0.91

 readers

0.87

 viewer

0.86

 listener

0.86

Activations Density 0.187%

statements commanding someone to do something

repetitions of the word "the."

No Comments

No Known Activations