INDEX

Explanations

expressions emphasizing a point or directive

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the verb "be" and its various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enegger

-0.51

again

-0.51

zik

-0.50

 moot

-0.50

è¦ļéĨĴ

-0.49

 again

-0.49

CVE

-0.48

sword

-0.47

theless

-0.44

 nets

-0.44

POSITIVE LOGITS

 Ezek

0.57

bold

0.54

six

0.52

tering

0.52

oud

0.51

ãĤ§

0.49

ornings

0.49

urations

0.47

oor

0.47

terness

0.47

Activations Density 0.346%

expressions emphasizing a point or directive

phrases emphasizing the verb "be" and its various forms

No Comments

No Known Activations