INDEX

Explanations

phrases related to arguments or justifications

oai_token-act-pair · gpt-3.5-turbo

the word "that" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Guard

-0.71

Plus

-0.68

Bonus

-0.67

EMBER

-0.67

gments

-0.66

guard

-0.65

Laughs

-0.62

RIP

-0.62

AND

-0.61

wn

-0.61

POSITIVE LOGITS

 they

0.75

 although

0.75

"[

0.74

cher

0.68

 prevailed

0.67

eday

0.65

 misunder

0.65

 "...

0.65

 there

0.64

it

0.63

Activations Density 0.196%

phrases related to arguments or justifications

the word "that" in various contexts

No Comments

No Known Activations