INDEX

Explanations

phrases related to legal allegations and judicial processes

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

0:0.04

1:0.02

2:0.07

3:0.05

4:0.06

5:0.04

6:0.33

7:0.06

8:0.04

9:0.17

10:0.02

11:0.03

Negative Logits

Theme

-4.09

Atl

-3.78

sym

-3.77

 Irma

-3.73

orea

-3.49

 resid

-3.44

 Shade

-3.39

gran

-3.35

Keys

-3.31

hattan

-3.28

POSITIVE LOGITS

cow

9.95

Cow

9.66

 cows

9.56

Cow

8.99

cow

8.38

 cattle

7.92

 Beef

6.30

 beef

6.10

 livestock

5.84

 pasture

5.76

Activations Density 0.004%

phrases related to legal allegations and judicial processes

No Comments

No Known Activations