INDEX

Explanations

proper names or nouns used to describe individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically people's names

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

pron

-0.67

uay

-0.66

taboola

-0.64

mble

-0.64

uminati

-0.60

berra

-0.59

į

-0.58

 âĢº

-0.57

abwe

-0.57

ymm

-0.57

POSITIVE LOGITS

's

0.70

kson

0.65

 herself

0.65

 wore

0.62

 swore

0.60

saw

0.59

 Introduced

0.58

 himself

0.57

 realised

0.57

owan

0.57

Activations Density 0.249%

proper names or nouns used to describe individuals

proper nouns, specifically people's names

No Comments

No Known Activations