INDEX

Explanations

instances where the document talks about the inclusion or incorporation of various items, concepts, or elements

oai_token-act-pair · gpt-3.5-turbo

phrases related to inclusion and context within discussions

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

ynchron

-0.73

agog

-0.73

chester

-0.72

MpServer

-0.66

uch

-0.66

uren

-0.65

lean

-0.65

agos

-0.64

bryce

-0.64

Eva

-0.64

POSITIVE LOGITS

 equation

1.18

 calculations

1.16

 calculation

1.02

 consideration

1.00

 discussions

0.94

 totals

0.92

 deliberations

0.89

 calculating

0.85

 calculus

0.85

 lieu

0.85

Activations Density 0.193%

instances where the document talks about the inclusion or incorporation of various items, concepts, or elements

phrases related to inclusion and context within discussions

No Comments

No Known Activations