INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names, particularly related to characters or entities within narratives

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 contrace

-0.71

 disadvant

-0.66

thia

-0.61

ortium

-0.60

 mosqu

-0.54

ãĤ¼ãĤ¦ãĤ¹

-0.52

 menus

-0.49

rast

-0.49

 phased

-0.48

sylv

-0.48

POSITIVE LOGITS

ugs

0.48

 sqor

0.48

 Sharif

0.46

gat

0.45

 Shotgun

0.45

minecraft

0.44

ï¸ı

0.44

keyes

0.44

sten

0.43

ooth

0.43

Activations Density 0.817%

names of individuals

proper nouns and names, particularly related to characters or entities within narratives

No Known Activations