INDEX

Explanations

questions asking for specific information

oai_token-act-pair · gpt-3.5-turbo

questions or phrases inquiring about quantities or measurements

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

usa

-0.70

ubs

-0.70

gin

-0.69

POST

-0.65

angelo

-0.63

hari

-0.63

aughed

-0.62

article

-0.62

ICA

-0.62

idia

-0.62

POSITIVE LOGITS

 much

1.36

far

1.12

 many

1.08

 badly

1.04

much

1.03

 long

1.01

 accurate

1.01

 MUCH

0.97

 Much

0.95

 efficiently

0.95

Activations Density 0.081%

questions asking for specific information

questions or phrases inquiring about quantities or measurements

No Comments

No Known Activations