INDEX

Explanations

proper nouns related to names of people, places, and organizations

oai_token-act-pair · gpt-3.5-turbo

references to the name "Jer", indicating a focus on people with that name

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

holders

-0.69

tumblr

-0.67

ULAR

-0.67

esan

-0.66

spring

-0.65

hetti

-0.64

ãģ¦

-0.63

Spread

-0.62

holder

-0.62

BOOK

-0.62

POSITIVE LOGITS

seys

1.35

usalem

1.07

Jer

1.06

miah

1.05

sey

0.84

jer

0.83

obo

0.82

ger

0.82

pee

0.79

uda

0.78

Activations Density 0.007%

proper nouns related to names of people, places, and organizations

references to the name "Jer", indicating a focus on people with that name

No Comments

No Known Activations