INDEX

Explanations

specific keywords and phrases related to announcements, information, and directives

oai_token-act-pair · gpt-3.5-turbo

thematic elements related to announcements and setups for future actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ãĤ¨ãĥ«

-0.62

ãĤ§

-0.61

ãĥİ

-0.55

alys

-0.55

sort

-0.55

uristic

-0.54

ãĤ¦ãĤ¹

-0.53

ãĤ¸

-0.53

capacity

-0.52

alysis

-0.52

POSITIVE LOGITS

 Panther

0.64

 Mehran

0.62

 America

0.61

 Gators

0.60

 Goldstein

0.60

 Hancock

0.59

 Ronnie

0.59

 Dame

0.59

 Colorado

0.59

 Kazakh

0.58

Activations Density 1.704%

specific keywords and phrases related to announcements, information, and directives

thematic elements related to announcements and setups for future actions or events

No Comments

No Known Activations