INDEX

Explanations

references to cooking and cheese recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.11

1:0.02

2:0.06

3:0.07

4:0.06

5:0.06

6:0.15

7:0.03

8:0.09

9:0.23

10:0.03

11:0.04

Negative Logits

 Tide

-3.49

··

-3.43

Bir

-3.35

soDeliveryDate

-3.35

atri

-3.32

undown

-3.22

 Pearson

-3.20

Thom

-3.16

 Beir

-3.14

amental

-3.13

POSITIVE LOGITS

 chees

8.30

 cheese

8.17

 Cheese

7.95

 dairy

4.77

 Chester

4.72

 cheesy

4.71

heddar

4.54

Che

4.49

 Dairy

4.44

che

4.17

Activations Density 0.009%

references to cooking and cheese recipes

No Comments

No Known Activations