INDEX

Explanations

markers indicating significant events or changes over time

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.18

1:0.03

2:0.15

3:0.13

4:0.03

5:0.05

6:0.06

7:0.14

8:0.03

9:0.05

10:0.04

11:0.04

Negative Logits

 Newark

-2.81

 negro

-2.78

 Newport

-2.48

rongh

-2.43

 Benghazi

-2.42

 Cornel

-2.34

 Gaddafi

-2.31

 cage

-2.23

 Libya

-2.21

 Libyan

-2.19

POSITIVE LOGITS

�

3.53

�

3.46

 Manit

3.27

 Katy

3.17

 Swift

3.09

�

3.04

�

2.97

Utt

2.96

 Scala

2.90

�

2.88

Activations Density 0.133%

markers indicating significant events or changes over time

No Comments

No Known Activations