INDEX

Explanations

references to significant events or impactful statements

oai_token-act-pair · gpt-3.5-turbo

sentences or phrases ending with punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

uers

-0.78

Ã¶n

-0.68

ascus

-0.68

RAW

-0.65

bra

-0.65

emonic

-0.64

 listener

-0.63

enary

-0.63

imb

-0.62

cho

-0.62

POSITIVE LOGITS

 Whereas

1.08

 Surely

1.07

But

1.06

 Worse

1.04

 Likewise

1.03

 They

1.00

 Then

0.99

 Moreover

0.99

 Granted

0.99

And

0.98

Activations Density 0.718%

references to significant events or impactful statements

sentences or phrases ending with punctuation

No Comments

No Known Activations