INDEX

Explanations

mentions of the term "Te" followed by a numerical value, specifically "Te 9" and "Te 10."

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "Te" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ItemTracker

-0.70

ividual

-0.68

thur

-0.68

 PRESS

-0.67

ãģį

-0.63

ãĤ¡

-0.63

IFIED

-0.63

âķĲ

-0.62

uitous

-0.62

éĹĺ

-0.61

POSITIVE LOGITS

achable

1.04

acher

1.03

aching

1.03

Te

0.99

arers

0.99

achers

0.96

aches

0.95

lem

0.95

akin

0.90

levision

0.88

Activations Density 0.006%

mentions of the term "Te" followed by a numerical value, specifically "Te 9" and "Te 10."

mentions of the word "Te" in various contexts

No Comments

No Known Activations