INDEX

Explanations

phrases related to making tasks more difficult or easier, especially in a legal or regulatory context

oai_token-act-pair · gpt-3.5-turbo

phrases indicating difficulties or challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

atur

-0.64

 Deaths

-0.61

ength

-0.61

 owes

-0.58

atures

-0.57

Shares

-0.56

 funer

-0.56

idth

-0.56

ennial

-0.56

Avg

-0.56

POSITIVE LOGITS

 easier

1.33

 impossible

1.15

 harder

1.14

 abundantly

1.08

 difficult

1.08

 possible

1.07

 unclear

1.03

 clearer

1.03

 clear

1.00

 easy

0.99

Activations Density 0.049%

phrases related to making tasks more difficult or easier, especially in a legal or regulatory context

phrases indicating difficulties or challenges

No Comments

No Known Activations