INDEX

Explanations

names of key political figures and officials

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.01

2:0.19

3:0.07

4:0.04

5:0.04

6:0.05

7:0.03

8:0.07

9:0.04

10:0.14

11:0.24

Negative Logits

office

-1.64

ghazi

-1.57

 Presidency

-1.50

judicial

-1.50

 presidency

-1.50

omaly

-1.47

 amen

-1.43

 captivity

-1.42

 Mubarak

-1.42

defense

-1.39

POSITIVE LOGITS

�醒

1.68

umers

1.54

ebted

1.48

��

1.48

)=(

1.42

Weather

1.39

ixt

1.33

 threaded

1.32

yrics

1.32

�

1.32

Activations Density 0.009%

names of key political figures and officials

No Comments

No Known Activations