INDEX

Explanations

legal terms related to court proceedings

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.04

1:0.02

2:0.14

3:0.04

4:0.29

5:0.06

6:0.02

7:0.03

8:0.04

9:0.19

10:0.05

11:0.02

Negative Logits

 Twisted

-1.41

ć

-1.38

ⓘ

-1.33

Saharan

-1.30

�

-1.30

Zi

-1.29

д

-1.29

Yaz

-1.27

 Czech

-1.26

 Kand

-1.24

POSITIVE LOGITS

 aloud

1.63

 ethics

1.55

 hearings

1.51

 Ethics

1.51

 Hear

1.41

 Starr

1.40

 deliberations

1.35

 Accountability

1.34

 podcasts

1.33

 congressional

1.32

Activations Density 0.006%

legal terms related to court proceedings

No Comments

No Known Activations