INDEX

Explanations

phrases related to locations or events occurring in specific places

oai_token-act-pair · gpt-3.5-turbo

the word "in" used in various contexts throughout the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

casters

-0.43

 accounted

-0.38

 therein

-0.37

—"

-0.37

tal

-0.36

 accordingly

-0.36

Though

-0.36

ispers

-0.36

¶æ

-0.35

 alternatively

-0.35

POSITIVE LOGITS

 vitro

0.70

 lieu

0.68

clusions

0.63

 accordance

0.62

clus

0.62

efficiency

0.62

 Tanzania

0.61

 favour

0.61

 Yugoslavia

0.60

 vivo

0.60

Activations Density 0.411%

phrases related to locations or events occurring in specific places

the word "in" used in various contexts throughout the document

No Comments

No Known Activations