INDEX

Explanations

phrases indicating change and uncertainty in situations

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.02

2:0.08

3:0.07

4:0.07

5:0.03

6:0.33

7:0.06

8:0.04

9:0.03

10:0.07

11:0.13

Negative Logits

[|

-1.49

 proposition

-1.33

+(

-1.26

 lifetime

-1.24

Poly

-1.22

ACA

-1.20

 predecessor

-1.19

College

-1.16

ONSORED

-1.16

Attempt

-1.15

POSITIVE LOGITS

icter

1.68

inflamm

1.50

ucket

1.45

roma

1.42

encia

1.39

nsics

1.35

hett

1.35

gettable

1.34

conservancy

1.34

ici

1.34

Activations Density 0.013%

phrases indicating change and uncertainty in situations

No Comments

No Known Activations