INDEX

Explanations

phrases and questions that express curiosity or seek information

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

0:0.01

1:0.01

2:0.08

3:0.18

4:0.08

5:0.03

6:0.07

7:0.06

8:0.05

9:0.05

10:0.17

11:0.16

Negative Logits

onomy

-1.60

estead

-1.49

hift

-1.47

pherd

-1.42

ş

-1.39

incial

-1.38

resident

-1.38

cult

-1.35

gd

-1.34

ploy

-1.34

POSITIVE LOGITS

 cracked

1.39

 curing

1.32

!).

1.28

)."

1.28

 Sponsor

1.27

Please

1.25

 expired

1.25

 guessed

1.25

 Schwarzenegger

1.23

 Comedy

1.21

Activations Density 0.001%

phrases and questions that express curiosity or seek information

No Comments

No Known Activations