INDEX

Explanations

instances of where a presentation is mentioned

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "presentation."

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

kowski

-0.74

apped

-0.72

leans

-0.72

cil

-0.64

sey

-0.64

si

-0.63

otrop

-0.63

chest

-0.62

 ILCS

-0.62

ranch

-0.62

POSITIVE LOGITS

 presentations

1.26

 presentation

1.15

eering

0.93

ocument

0.91

 slides

0.88

 Present

0.84

nce

0.76

DragonMagazine

0.75

ļéĨĴ

0.74

emonium

0.74

Activations Density 0.011%

instances of where a presentation is mentioned

occurrences of the word "presentation."

No Comments

No Known Activations