INDEX

Explanations

names of individuals or entities in quotes

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people or characters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥ¼ãĥĨ

-0.61

ĸļ

-0.60

 Thumbnails

-0.58

tumblr

-0.54

 destro

-0.51

 Cerberus

-0.51

åĤ

-0.51

è¦ļéĨĴ

-0.51

*.

-0.51

 womb

-0.50

POSITIVE LOGITS

ham

0.59

ente

0.59

sey

0.59

elli

0.58

han

0.58

mar

0.58

aj

0.58

anta

0.58

ena

0.57

hend

0.57

Activations Density 0.670%

names of individuals or entities in quotes

proper nouns, specifically names of people or characters

No Comments

No Known Activations