INDEX

Explanations

expressions indicating certainty or likelihood of events

oai_token-act-pair · gpt-3.5-turbo

phrases that express negation or disbelief regarding various situations or statements

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

kefeller

-0.74

 Citiz

-0.65

escription

-0.64

İĭ

-0.60

DragonMagazine

-0.58

apons

-0.57

anian

-0.57

 pione

-0.57

artney

-0.56

isin

-0.56

POSITIVE LOGITS

1.08

 ðŁĻĤ

1.01

1.00

 Nope

0.99

!!!!

0.98

!!!

0.97

!!

0.93

!.

0.93

*.

0.90

%.

0.89

Activations Density 0.204%

expressions indicating certainty or likelihood of events

phrases that express negation or disbelief regarding various situations or statements

No Comments

No Known Activations