INDEX

Explanations

terms related to commands, instructions, or procedures

oai_token-act-pair · gpt-3.5-turbo

instances of Pokémon

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 helicop

-0.52

enegger

-0.50

 disadvant

-0.50

jri

-0.48

 destro

-0.47

 nomine

-0.46

 hemor

-0.45

Interstitial

-0.45

nesday

-0.45

,...

-0.44

POSITIVE LOGITS

\":

0.48

photos

0.48

º

0.47

®

0.47

 âĢº

0.43

alyses

0.41

§

0.41

Ĥª

0.41

IGHTS

0.40

ļ

0.40

Activations Density 1.894%

terms related to commands, instructions, or procedures

instances of Pokémon

No Comments

No Known Activations